© 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. 12298
    Prev
    Next
    INDEX
    Explanations

    instruction statements or definitions

    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
    二次
    -1.01
     exten
    -0.90
    énage
    -0.89
    節約
    -0.87
     on
    -0.86
    二度
    -0.85
     angusti
    -0.83
    cipta
    -0.83
    atação
    -0.81
    再次
    -0.81
    POSITIVE LOGITS
     dianggap
    1.21
     enseñanza
    1.18
     pourrait
    1.16
     such
    1.15
     instructions
    1.14
     Fácil
    1.14
    sequence
    1.13
     sequence
    1.13
    の種類
    1.13
    ieme
    1.09
    Activations Density 0.029%

    No Known Activations