© 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. 102861
    Prev
    Next
    INDEX
    Explanations

    it just so happens

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    ArgsConstructor
    -0.91
    setVerticalGroup
    -0.88
    orova
    -0.88
    paradise
    -0.88
    readFileSync
    -0.87
    consulté
    -0.85
    كويكب
    -0.84
    bayern
    -0.84
     بودند
    -0.84
    bershka
    -0.83
    POSITIVE LOGITS
     happen
    4.75
     happens
    4.63
     happened
    3.92
    剛好
    3.02
     coincident
    2.98
    happens
    2.97
    happen
    2.94
    恰
    2.84
    たまたま
    2.80
     Happens
    2.69
    Activations Density 0.074%

    No Known Activations