© 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. 7766
    Prev
    Next
    INDEX
    Explanations

    numerical identifiers

    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
    i
    -4.03
    ي
    -2.61
    a
    -2.52
    ቭ
    -2.17
    नलोड
    -2.11
     Reſ
    -2.08
     עם
    -2.05
    翼翼
    -2.03
     tidak
    -2.02
     berbagai
    -2.00
    POSITIVE LOGITS
    ם
    2.42
    ید
    2.16
    茱
    2.14
    ية
    2.06
    </h3>
    2.03
    нией
    2.02
    谁能
    2.02
    込んだ
    1.98
    礻
    1.97
    姸
    1.97
    Activations Density 0.001%

    No Known Activations