© 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. 44463
    Prev
    Next
    INDEX
    Explanations

    Powell and Palmer names

    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
    .
    -3.34
    *
    -2.52
     большое
    -2.47
    ↵↵
    -2.41
     Those
    -2.38
    on
    -2.36
    你看
    -2.31
     You
    -2.31
    t
    -2.27
     Our
    -2.19
    POSITIVE LOGITS
    葙
    2.98
    咵
    2.98
     guardado
    2.80
     interactiva
    2.80
    ᯾
    2.78
    樒
    2.72
    ⚢
    2.70
    쨩
    2.69
    meteries
    2.63
    乄
    2.63
    Activations Density 0.004%

    No Known Activations