© 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. 59704
    Prev
    Next
    INDEX
    Explanations

    discuss, explain, describe

    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
     både
    -2.92
     zowel
    -1.95
    跸
    -1.95
     quería
    -1.93
     zarówno
    -1.92
     rekan
    -1.92
    ཫ
    -1.91
     sekä
    -1.91
     aisladas
    -1.86
    rsquo
    -1.85
    POSITIVE LOGITS
    </h2>
    2.42
     ensure
    2.20
     increase
    2.19
    Because
    2.09
     can
    2.02
    They
    1.99
    This
    1.98
     actually
    1.90
     recommend
    1.88
     will
    1.88
    Activations Density 0.049%

    No Known Activations