© 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. 11502
    Prev
    Next
    INDEX
    Explanations

    following sequenced states

    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
     بناء
    -1.02
    Fixes
    -0.91
    yoruz
    -0.90
     куртка
    -0.89
     dopln
    -0.88
    Repair
    -0.86
    ργο
    -0.83
     Externe
    -0.83
    idespread
    -0.83
    ENSATION
    -0.82
    POSITIVE LOGITS
     after
    1.80
     afterwards
    1.52
     после
    1.32
     afterward
    1.31
    После
    1.23
     continue
    1.17
     remaining
    1.13
     після
    1.13
     depois
    1.12
     still
    1.11
    Activations Density 0.052%

    No Known Activations