© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 92917
    Prev
    Next
    INDEX
    Explanations

    numbers followed by 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
     deportivas
    -1.88
     what
    -1.74
     There
    -1.55
     how
    -1.54
     even
    -1.53
     give
    -1.53
    there
    -1.49
     says
    -1.48
     after
    -1.46
     that
    -1.43
    POSITIVE LOGITS
    </em>
    2.13
    '
    1.93
    ’
    1.88
     probablement
    1.61
     voyant
    1.59
    </i>
    1.57
     donnant
    1.51
     faciles
    1.50
     bestellen
    1.44
     utiles
    1.41
    Activations Density 0.009%

    No Known Activations