© 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. 15026
    Prev
    Next
    INDEX
    Explanations

    Shader followed by specific syntax

    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
     ドラゴン
    -1.14
     drôle
    -1.10
    ruka
    -1.08
    Также
    -1.06
     når
    -1.03
    もちゃ
    -1.02
    📁
    -1.02
    蚋
    -1.02
    utando
    -1.02
    как
    -1.02
    POSITIVE LOGITS
    </i>
    1.20
     like
    1.20
    ﾋ
    1.08
    ption
    1.05
    』。
    1.03
    同様
    1.00
    していて
    0.98
    1
    0.98
     but
    0.97
    ější
    0.97
    Activations Density 0.060%

    No Known Activations