© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 76305
    Prev
    Next
    INDEX
    Explanations

    Q: or type

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron is specialized to detect software license or copyright header blocks (e.g. comment-style copyright notices and related boilerplate).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    C/C++ source code with preprocessor directives and header-guard style boilerplate.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408

    programming code, particularly in structured technical documents like source code files, patent specifications, or HTML/CSS files.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     <<<<<<<<<<<<<<
    -0.73
     Papst
    -0.71
     chloroform
    -0.70
    GAS
    -0.70
     royalty
    -0.69
     smoking
    -0.68
    اد
    -0.68
     semper
    -0.67
    zeu
    -0.67
    గు
    -0.67
    POSITIVE LOGITS
     Tor
    1.22
     onion
    1.09
    Tor
    1.09
     tor
    1.02
    tor
    1.00
     Onion
    0.96
     TOR
    0.92
     relays
    0.90
    Onion
    0.88
     relay
    0.88
    Activations Density 0.017%

    No Known Activations