© 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. 22-GEMMASCOPE-RES-131K
    7. 34311
    Prev
    Next
    INDEX
    Explanations

    labels after punctuation

    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_22/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
     musst
    -1.27
    thmus
    -1.20
    chemia
    -1.20
    trell
    -1.16
     quitte
    -1.14
     eventi
    -1.14
    ⿻
    -1.13
    rée
    -1.11
     wann
    -1.09
    ofus
    -1.09
    POSITIVE LOGITS
     Various
    1.27
    まれた
    1.25
     ziemlich
    1.16
     various
    1.15
     Mostly
    1.14
     meistens
    1.11
     bisschen
    1.09
     Mainly
    1.09
     канди
    1.08
     Recently
    1.07
    Activations Density 0.006%

    No Known Activations