© 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. 71664
    Prev
    Next
    INDEX
    Explanations

    public domain

    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
    </i>
    -1.81
     momentous
    -1.73
    尬
    -1.70
    
    -1.64
     verwendet
    -1.63
     usado
    -1.59
    釤
    -1.59
     considerado
    -1.57
    XXV
    -1.55
    StoryboardSegue
    -1.53
    POSITIVE LOGITS
    ↵
    2.28
    However
    2.06
    mathrm
    1.80
    There
    1.77
     dekoratif
    1.67
    Despite
    1.62
    While
    1.58
    ATHERINE
    1.58
    ші
    1.53
     adanya
    1.50
    Activations Density 0.037%

    No Known Activations