© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 115950
    Prev
    Next
    INDEX
    Explanations

    as is agreement

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

    This neuron fires on boilerplate license‐and‐copyright comment text (e.g. words like “file,” “license,” “we’re willing to,” “distributed,” 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
     at
    -1.56
     without
    -1.52
     or
    -1.45
     provides
    -1.45
     provide
    -1.41
     striving
    -1.36
     steadily
    -1.36
     during
    -1.35
     should
    -1.34
     in
    -1.33
    POSITIVE LOGITS
     Dinas
    1.43
     ſon
    1.31
    probably
    1.30
     your
    1.30
    
    1.23
     goofy
    1.21
     เว
    1.20
     quirky
    1.20
    primarily
    1.20
    really
    1.19
    Activations Density 0.002%

    No Known Activations