© 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. 59979
    Prev
    Next
    INDEX
    Explanations

    in all of

    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
     editados
    -1.63
    这种
    -1.56
     THESE
    -1.47
     perdidos
    -1.46
     هذه
    -1.36
     usados
    -1.34
    </h3>
    -1.32
    iramente
    -1.31
    躂
    -1.27
     使っ
    -1.26
    POSITIVE LOGITS
     only
    1.61
     their
    1.53
     Only
    1.48
    raisemb
    1.40
     ONLY
    1.33
     تنها
    1.31
     wahrscheinlich
    1.29
    ߳
    1.27
     entire
    1.27
    новение
    1.27
    Activations Density 0.011%

    No Known Activations