© 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. 7656
    Prev
    Next
    INDEX
    Explanations

    year, days, numbers

    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
    </h2>
    -2.08
    皷
    -2.02
     cujo
    -2.02
    ৄ
    -2.00
    
    -1.93
     conhecido
    -1.91
    
    -1.89
    跸
    -1.88
    ")]
    -1.78
    晄
    -1.77
    POSITIVE LOGITS
    They
    2.64
     They
    2.41
    they
    2.33
    There
    2.31
    le
    2.28
     mereka
    2.14
    this
    2.02
    AT
    1.98
    just
    1.95
    IT
    1.93
    Activations Density 0.008%

    No Known Activations