© 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. 65516
    Prev
    Next
    INDEX
    Explanations

    quantifiers, numbers, and common words

    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
     only
    -1.83
     is
    -1.76
     other
    -1.75
     always
    -1.51
    .
    -1.47
    E
    -1.47
     these
    -1.46
     often
    -1.46
    ?
    -1.45
     also
    -1.44
    POSITIVE LOGITS
    تصویر
    1.75
    ごめん
    1.69
    久し
    1.68
     repuesto
    1.66
     trajets
    1.65
     nadru
    1.61
    にほんブログ村
    1.60
     dátum
    1.59
     réinitial
    1.59
     giyim
    1.59
    Activations Density 0.126%

    No Known Activations