© 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. 84568
    Prev
    Next
    INDEX
    Explanations

    gases, icosahedral, warrants

    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
    いかがでしたか
    -1.73
    そういえば
    -1.72
    Always
    -1.68
     you
    -1.61
    ついでに
    -1.59
    こんな感じで
    -1.56
    Not
    -1.56
    Being
    -1.55
    このように
    -1.55
    Some
    -1.55
    POSITIVE LOGITS
    𐐀
    1.65
    鬭
    1.59
     azzurro
    1.58
    の人に
    1.56
    躂
    1.55
     again
    1.55
     autunno
    1.54
    duino
    1.54
     itinéraires
    1.51
    毉
    1.51
    Activations Density 0.034%

    No Known Activations