© 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. 21004
    Prev
    Next
    INDEX
    Explanations

    hands-on

    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
    </i>
    -2.06
    </td>
    -1.88
    '
    -1.77
    頗
    -1.56
     comanda
    -1.56
     ""));
    -1.55
     дорогой
    -1.53
    </h5>
    -1.52
     cherokee
    -1.52
    說的
    -1.52
    POSITIVE LOGITS
     impede
    1.89
    箝
    1.88
     reputable
    1.77
    ๋า
    1.77
    仍然
    1.72
     sehingga
    1.72
     afectadas
    1.71
    蓴
    1.70
    ícios
    1.69
     humaine
    1.68
    Activations Density 0.007%

    No Known Activations