© 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. 14620
    Prev
    Next
    INDEX
    Explanations

    want, wish, or choose

    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
     tolerable
    -1.23
     Они
    -1.23
     cursory
    -1.14
     nuovo
    -1.12
    newData
    -1.11
    使った
    -1.07
    ípios
    -1.06
     geomet
    -1.05
    Pcs
    -1.05
     wyja
    -1.04
    POSITIVE LOGITS
     اگر
    1.43
     ninguém
    1.36
     если
    1.35
     NSCoder
    1.34
    makeatother
    1.33
    ."
    1.32
    quirer
    1.31
    tainable
    1.31
     любую
    1.29
    ).
    1.26
    Activations Density 0.009%

    No Known Activations