© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 80716
    Prev
    Next
    INDEX
    Explanations

    class field names

    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
     vijf
    -2.09
    archiwizowane
    -1.99
     samarbeid
    -1.82
     continúas
    -1.82
    during
    -1.78
    粜
    -1.78
    having
    -1.76
     presque
    -1.76
     bijna
    -1.74
    🫱
    -1.73
    POSITIVE LOGITS
    </td>
    2.36
     This
    2.06
     However
    1.93
    </h2>
    1.85
     There
    1.79
     which
    1.71
    .'"
    1.70
     Also
    1.66
    とはいえ
    1.59
     beserta
    1.57
    Activations Density 0.018%

    No Known Activations