© 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. 60167
    Prev
    Next
    INDEX
    Explanations

    parent in code

    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
    on
    -2.25
    </h3>
    -1.91
    '
    -1.85
    *
    -1.81
    it
    -1.75
     এবং
    -1.74
    "
    -1.73
     fechar
    -1.73
    no
    -1.70
    al
    -1.69
    POSITIVE LOGITS
    Ꭳ
    2.05
    नलोड
    1.96
    
    1.95
     glamorous
    1.92
    parent
    1.89
     anstatt
    1.84
    犇
    1.80
    Sábado
    1.76
     jóvenes
    1.76
    demás
    1.73
    Activations Density 0.003%

    No Known Activations