© 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. 750
    Prev
    Next
    INDEX
    Explanations

    posted by or on

    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
    ፨
    -1.72
    quirrel
    -1.63
    蟥
    -1.59
    avn
    -1.56
    ℣
    -1.52
     frequentemente
    -1.51
    ⽇
    -1.50
    amsung
    -1.50
    ⎻
    -1.49
     repuesto
    -1.48
    POSITIVE LOGITS
    Maybe
    1.78
     They
    1.78
    end
    1.75
    Not
    1.70
     there
    1.66
    s
    1.65
    Get
    1.63
     it
    1.59
    Have
    1.59
    there
    1.57
    Activations Density 0.034%

    No Known Activations