© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 85617
    Prev
    Next
    INDEX
    Explanations

    as far as

    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
    俢
    -1.76
    芣
    -1.70
    蒾
    -1.67
     cibo
    -1.67
    
    -1.66
     dieser
    -1.64
     cansado
    -1.59
    苼
    -1.59
     tornillos
    -1.55
     haline
    -1.55
    POSITIVE LOGITS
     to
    2.89
     the
    2.58
     it
    1.89
     Its
    1.78
     einschließlich
    1.74
     individuellen
    1.73
     llevará
    1.70
    心疼
    1.70
    ang
    1.70
    in
    1.69
    Activations Density 0.006%

    No Known Activations