© 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. 8092
    Prev
    Next
    INDEX
    Explanations

    dates and titles

    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
     knows
    -1.62
    你现在
    -1.56
     that
    -1.51
    ときに
    -1.49
     bestaat
    -1.45
    何より
    -1.38
    ()['
    -1.34
    isierte
    -1.34
     contains
    -1.30
    Dimens
    -1.27
    POSITIVE LOGITS
    СИ
    1.54
    ↵↵
    1.34
    </h2>
    1.32
    ма
    1.27
    </h1>
    1.23
    lysm
    1.20
    印象
    1.20
     急
    1.20
     enduring
    1.19
     usando
    1.18
    Activations Density 0.044%

    No Known Activations