© 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. 109870
    Prev
    Next
    INDEX
    Explanations

    name parts

    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
    ભ
    -0.87
     состави
    -0.79
    ♢
    -0.77
    ombang
    -0.77
    ファイルを
    -0.77
    تي
    -0.75
     جنوبی
    -0.74
    গ
    -0.73
     beras
    -0.71
     TAPE
    -0.70
    POSITIVE LOGITS
     nightfall
    0.79
    Firewall
    0.79
    BTN
    0.78
    र्क
    0.77
    不明白
    0.75
     beet
    0.75
     Galveston
    0.73
    }=$
    0.73
     moat
    0.73
    ねぎ
    0.72
    Activations Density 0.086%

    No Known Activations