© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 67632
    Prev
    Next
    INDEX
    Explanations

    SO followed by number

    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
     hermosas
    -2.63
    
    -2.53
     hermosos
    -2.47
     ہیں
    -2.31
    ﺲ
    -2.31
     Ganzen
    -2.23
    
    -2.22
     Monaten
    -2.22
     autory
    -2.20
     texturas
    -2.11
    POSITIVE LOGITS
                
    2.88
    ↵
    2.22
    *
    2.17
    <strong>
    2.03
    𓐍
    2.00
    ’
    1.98
    渼
    1.97
       
    1.95
    ↵↵
    1.92
     Acknowled
    1.88
    Activations Density 0.019%

    No Known Activations