© 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. 72793
    Prev
    Next
    INDEX
    Explanations

    thank you so much for

    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
    ႐
    -1.88
    汌
    -1.84
    って何
    -1.80
     TAMBIÉN
    -1.62
     défaite
    -1.62
     felicità
    -1.58
     with
    -1.49
    ၠ
    -1.46
     disfrute
    -1.45
     következő
    -1.45
    POSITIVE LOGITS
     是
    1.53
    <bos>
    1.51
     estekak
    1.49
     позволя
    1.44
     这
    1.44
    0
    1.38
    .
    1.37
     Islas
    1.34
    依旧
    1.34
    5
    1.34
    Activations Density 0.003%

    No Known Activations