© 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. 109744
    Prev
    Next
    INDEX
    Explanations

    zone, league, county, province

    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
    ouwen
    -0.79
    cfd
    -0.78
     להת
    -0.77
     recherches
    -0.73
     azul
    -0.73
    igure
    -0.71
     araştır
    -0.71
     trow
    -0.70
     renou
    -0.69
     objectifs
    -0.69
    POSITIVE LOGITS
     heat
    0.84
     Jap
    0.81
    Subset
    0.80
    elancer
    0.79
    Ԫ
    0.77
     financière
    0.76
     receives
    0.75
     Ebene
    0.73
    commodations
    0.73
    あれば
    0.72
    Activations Density 0.017%

    No Known Activations