© 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. 90232
    Prev
    Next
    INDEX
    Explanations

    BSD-style license comments

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

    The neuron is triggered by terms in source‐code header comments and directives that belong to license or copyright boilerplate (e.g. “reserved,” “license,” “governed,” “include,” “found,” etc.).

    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
     inner
    -0.87
     органов
    -0.79
    inner
    -0.79
    mActivity
    -0.73
    hausen
    -0.71
     serveur
    -0.70
     MATT
    -0.70
    coj
    -0.69
    ladı
    -0.69
     guerres
    -0.69
    POSITIVE LOGITS
    ショップ
    0.71
     sequence
    0.71
    يال
    0.71
    combobox
    0.71
    Sequence
    0.70
     lipo
    0.70
     WS
    0.70
    WS
    0.69
    hawat
    0.69
     Sequence
    0.68
    Activations Density 0.086%

    No Known Activations