© 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. 60819
    Prev
    Next
    INDEX
    Explanations

    teams and leaders

    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
     două
    -1.55
     where
    -1.42
     zawsze
    -1.28
     incidents
    -1.26
     ثلاثة
    -1.22
    ingos
    -1.16
     diventare
    -1.15
     diferite
    -1.13
     чаще
    -1.10
    ских
    -1.09
    POSITIVE LOGITS
    حياته
    1.31
    wego
    1.20
    äß
    1.16
     (
    1.13
     guste
    1.10
    <tbody>
    1.09
     heeft
    1.07
    ㅕ
    1.07
     pertinentes
    1.07
     tarafından
    1.06
    Activations Density 0.069%

    No Known Activations