© 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. 44551
    Prev
    Next
    INDEX
    Explanations

    in terms of

    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
    ſſen
    -1.95
    鹩
    -1.81
    ⚣
    -1.73
     manicura
    -1.63
    ◔
    -1.61
     fiabilidad
    -1.55
     asegurarse
    -1.51
    </b>
    -1.51
    ￬
    -1.51
     вашу
    -1.50
    POSITIVE LOGITS
     our
    2.33
     by
    1.95
     some
    1.93
     both
    1.77
     other
    1.77
     with
    1.73
     those
    1.73
     another
    1.70
     reinforces
    1.63
     various
    1.62
    Activations Density 0.019%

    No Known Activations