© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 12162
    Prev
    Next
    INDEX
    Explanations

    mathematical sets and sequences

    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_22/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
     tár
    -0.88
     fundador
    -0.86
     infinite
    -0.85
     assuré
    -0.85
     comuniques
    -0.84
     guerres
    -0.84
     iterative
    -0.83
    infinite
    -0.82
     actualizado
    -0.82
     latine
    -0.82
    POSITIVE LOGITS
     then
    0.82
    閻
    0.81
    Fatalf
    0.79
     perhaps
    0.78
     compared
    0.77
     Reson
    0.77
     SNMP
    0.75
    一周
    0.72
     Bim
    0.72
    效
    0.71
    Activations Density 0.095%

    No Known Activations