© 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. 10-GEMMASCOPE-RES-131K
    4. 42244
    Prev
    Next
    INDEX
    Explanations

    required by

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

    This neuron fires on formal license‐and legal‐boilerplate language (e.g. “licensed under,” “unless required by applicable law,” license URLs, 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_10/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
     malgré
    -1.63
     största
    -1.57
     cial
    -1.52
     menthe
    -1.52
    ;(
    -1.50
    
    -1.49
    ditionally
    -1.48
     dieu
    -1.48
    都已经
    -1.46
     ular
    -1.46
    POSITIVE LOGITS
     at
    2.64
     by
    2.42
     and
    2.14
     as
    1.95
     or
    1.84
     There
    1.73
     there
    1.66
     seemed
    1.64
     epitom
    1.63
     one
    1.59
    Activations Density 0.282%

    No Known Activations