© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 128583
    Prev
    Next
    INDEX
    Explanations

    special characters and punctuation

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

    The neuron fires on longer alphanumeric tokens—typically multi-character identifiers or variable/function names.

    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
     for
    -2.89
     or
    -2.58
    ;
    -2.41
     of
    -2.38
     only
    -2.33
     with
    -2.31
     but
    -2.28
     every
    -2.23
     both
    -2.22
     so
    -2.13
    POSITIVE LOGITS
    扨
    2.14
     exemplaire
    1.98
    猛地
    1.95
    乄
    1.92
    
    1.90
     quintessential
    1.88
    嗩
    1.86
     mejoras
    1.84
     Belgische
    1.84
     huidige
    1.82
    Activations Density 0.002%

    No Known Activations