© 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. 59551
    Prev
    Next
    INDEX
    Explanations

    equivalence or equivalent concepts

    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
    癭
    -2.67
     serán
    -2.52
    ка
    -2.27
    所有人都
    -2.23
    </i>
    -2.22
    腘
    -2.19
    
    -2.17
     ストライプ
    -2.14
     ort
    -2.14
    untuk
    -2.14
    POSITIVE LOGITS
     That
    2.33
     Seems
    2.27
     और
    2.27
     Another
    2.17
    !!!!!
    2.11
     Shortly
    2.08
     ONLY
    2.08
     Obviously
    2.05
     邊
    2.03
    !!!!
    2.02
    Activations Density 0.012%

    No Known Activations