© 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. 34-GEMMASCOPE-RES-131K
    7. 110478
    Prev
    Next
    INDEX
    Explanations

    this permission

    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
    ಗ
    -0.75
    ترك
    -0.73
    COLOR
    -0.72
     XVI
    -0.71
     ロング
    -0.70
    Long
    -0.70
    ම
    -0.69
    Od
    -0.69
    liese
    -0.68
    шот
    -0.67
    POSITIVE LOGITS
    第二个
    0.73
    辅导
    0.70
     CRUD
    0.67
    bsc
    0.66
    けど
    0.63
    Tobi
    0.63
    ꪀ
    0.63
     insult
    0.62
    afi
    0.62
    orti
    0.62
    Activations Density 0.100%

    No Known Activations