© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 113528
    Prev
    Next
    INDEX
    Explanations

    origin or source

    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
     больших
    -1.57
    </h6>
    -1.54
    </h2>
    -1.52
    ());
    -1.47
     poderá
    -1.44
     réalisées
    -1.42
     erfordert
    -1.42
    上がった
    -1.41
     chcesz
    -1.39
    this
    -1.38
    POSITIVE LOGITS
     standpoint
    2.09
     afar
    1.90
     whence
    1.84
     across
    1.73
     using
    1.66
     from
    1.66
     طریق
    1.63
     segi
    1.61
     by
    1.61
    ркут
    1.54
    Activations Density 0.273%

    No Known Activations