© 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. 10-GEMMASCOPE-RES-131K
    7. 573
    Prev
    Next
    INDEX
    Explanations

    what questions

    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_10/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
     vider
    -2.17
    ientras
    -2.05
     somewhat
    -2.03
     selben
    -2.00
    ین
    -1.98
    𓆏
    -1.97
     Pläne
    -1.95
    และ
    -1.94
     xviii
    -1.93
     què
    -1.91
    POSITIVE LOGITS
     gave
    2.19
    ↵↵
    2.13
     What
    2.03
    Why
    2.02
     gives
    1.97
    How
    1.97
     Why
    1.90
     ....
    1.89
     went
    1.89
     .....
    1.88
    Activations Density 0.058%

    No Known Activations