© 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. 11329
    Prev
    Next
    INDEX
    Explanations

    sentence starters

    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
     giapponese
    -1.20
     Stadion
    -1.16
     umo
    -1.16
     talle
    -1.12
     itſelf
    -1.11
     taba
    -1.07
     himo
    -1.06
    lieving
    -1.06
     espagnol
    -1.06
     MUNICIP
    -1.06
    POSITIVE LOGITS
     and
    1.30
     там
    1.02
    rekli
    0.98
     is
    0.94
    sena
    0.94
     erreichbar
    0.93
     возможности
    0.93
    嘢
    0.93
    一回
    0.93
    ズの
    0.92
    Activations Density 0.000%

    No Known Activations