© 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. 100275
    Prev
    Next
    INDEX
    Explanations

    ordinal numbers followed by comma

    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
     -
    -1.78
     видит
    -1.74
     totalité
    -1.70
    现有
    -1.66
     împre
    -1.66
    up
    -1.66
    不断
    -1.64
     only
    -1.59
    </h4>
    -1.59
    比べて
    -1.56
    POSITIVE LOGITS
    獃
    1.87
    ."
    1.79
    內容簡介
    1.72
    The
    1.66
    ########.
    1.65
     estekak
    1.62
    )
    1.61
    似乎
    1.60
     Exceptional
    1.60
    鹛
    1.59
    Activations Density 0.007%

    No Known Activations