© 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. 68174
    Prev
    Next
    INDEX
    Explanations

    Android resource identifiers

    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
     that
    -2.17
    It
    -1.91
    </th>
    -1.85
     also
    -1.84
     Also
    -1.81
     When
    -1.67
    Also
    -1.66
    )
    -1.65
     It
    -1.57
     At
    -1.57
    POSITIVE LOGITS
     ένα
    1.79
     creador
    1.64
     quatro
    1.51
    幛
    1.47
    只好
    1.44
    tualmente
    1.40
    棡
    1.37
    蓐
    1.36
     diseñador
    1.36
     oficjal
    1.33
    Activations Density 0.001%

    No Known Activations