© 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. 48712
    Prev
    Next
    INDEX
    Explanations

    software license disclaimers

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

    The neuron strongly activates on tokens from Apache‐style license headers (in particular the word “software” and related boilerplate).

    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
    SuppressLint
    -0.73
    idiv
    -0.69
     Role
    -0.65
     INJ
    -0.64
    nass
    -0.63
     jumbo
    -0.62
     Sycamore
    -0.62
    icare
    -0.61
    ättning
    -0.59
     magna
    -0.59
    POSITIVE LOGITS
    ꒦
    0.73
    tanh
    0.69
    istischen
    0.68
    推送
    0.65
     Respir
    0.65
    齢
    0.64
     Sadler
    0.64
    aménagement
    0.63
    distribution
    0.63
    profil
    0.62
    Activations Density 0.162%

    No Known Activations