© 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. 127703
    Prev
    Next
    INDEX
    Explanations

    appropriateness of something

    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
    iconductors
    -1.86
     surpass
    -1.77
    푉
    -1.77
     wither
    -1.77
    ᥬ
    -1.75
    </h2>
    -1.72
    蝨
    -1.72
    archiwizowane
    -1.71
     $-$
    -1.69
     inim
    -1.69
    POSITIVE LOGITS
    U
    2.06
     enticing
    1.92
    ஂ
    1.91
    蛧
    1.83
     artesanal
    1.83
    劻
    1.83
    鏵
    1.83
    appropriate
    1.81
    n
    1.77
     heightened
    1.77
    Activations Density 0.017%

    No Known Activations