© 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. 690
    Prev
    Next
    INDEX
    Explanations

    database terms and identifiers

    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
     It
    -2.73
    潆
    -2.61
    isation
    -2.52
    ），
    -2.52
    驁
    -2.48
    唞
    -2.47
    ated
    -2.44
     มัน
    -2.41
    ния
    -2.38
     That
    -2.31
    POSITIVE LOGITS
    \
    2.64
    
    2.58
    db
    2.53
    I
    2.47
    am
    2.30
     coraz
    2.28
     ensure
    2.28
    欒
    2.27
    战胜
    2.25
    }$
    2.23
    Activations Density 0.018%

    No Known Activations