© 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. 91339
    Prev
    Next
    INDEX
    Explanations

    java code keywords and types

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

    This neuron fires on numeric tokens (digits or number literals) in the text.

    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
     unless
    -0.95
     it
    -0.90
     особли
    -0.89
     instead
    -0.86
     Genehmigung
    -0.82
     вже
    -0.81
     пев
    -0.80
     близь
    -0.79
     except
    -0.79
     during
    -0.79
    POSITIVE LOGITS
    var
    2.92
     var
    2.39
    final
    1.88
     final
    1.80
    VAR
    1.31
    Var
    1.25
    Optional
    1.20
    Long
    1.17
     VAR
    1.16
    String
    1.13
    Activations Density 0.004%

    No Known Activations