© 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. 60371
    Prev
    Next
    INDEX
    Explanations

    HTML attribute names and values

    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
     to
    -1.83
    dération
    -1.45
     ausgesprochen
    -1.41
    してました
    -1.39
     was
    -1.38
    してた
    -1.30
     what
    -1.30
    どういう
    -1.30
     alike
    -1.28
    一切都
    -1.28
    POSITIVE LOGITS
    </sup>
    1.91
    prender
    1.73
    </h2>
    1.68
     comportements
    1.59
    tividade
    1.59
    を開始
    1.58
     prato
    1.57
    𓆜
    1.55
    </b>
    1.54
    伱
    1.54
    Activations Density 0.022%

    No Known Activations