© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 12068
    Prev
    Next
    INDEX
    Explanations

    personalization and customization

    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
    .
    -3.36
    </h3>
    -2.88
     Primarily
    -2.77
     Ironically
    -2.67
     Surprisingly
    -2.63
     незавер
    -2.52
     Essentially
    -2.47
    酲
    -2.45
     Seems
    -2.45
     Obviously
    -2.42
    POSITIVE LOGITS
     dando
    2.69
    </b>
    2.59
     '"
    2.45
     "
    2.30
     frequentemente
    2.19
    ’
    2.17
     The
    2.16
     .......
    2.11
     głównie
    2.11
     mostrando
    2.09
    Activations Density 0.012%

    No Known Activations