© 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. 20841
    Prev
    Next
    INDEX
    Explanations

    a/an followed by descriptive words

    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
     of
    -2.63
    by
    -2.08
     by
    -2.03
     two
    -2.00
     puas
    -1.99
     cerdas
    -1.99
     istimewa
    -1.92
     signifikan
    -1.82
     strategis
    -1.80
     three
    -1.77
    POSITIVE LOGITS
    十分的
    2.00
    </h2>
    1.89
     ใน
    1.84
     also
    1.75
    pulseira
    1.73
    以免
    1.67
     extremamente
    1.60
    ↵↵
    1.59
     apesar
    1.56
     całego
    1.56
    Activations Density 0.093%

    No Known Activations