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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 79180
    Prev
    Next
    INDEX
    Explanations

    Special Interest Sites

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

    The neuron spikes on tokens that are parts of code/markup identifiers and file‐path or namespace strings—i.e. bits containing punctuation like dots or angle brackets found in filenames, class names, and XML/HTML tags.

    oai_token-act-pair · o4-miniTriggered 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
    清晨
    -0.81
     stří
    -0.67
     embryo
    -0.66
    fl
    -0.66
     Type
    -0.66
    Sn
    -0.64
    ESCAPE
    -0.64
     argv
    -0.63
     Vy
    -0.63
    mea
    -0.62
    POSITIVE LOGITS
    Compet
    0.71
    yszer
    0.71
    obra
    0.69
    բ
    0.69
    Ranger
    0.69
    Excellence
    0.68
    Yale
    0.66
    mHandler
    0.66
     استاد
    0.65
    anna
    0.65
    Activations Density 0.064%

    No Known Activations