© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 20609
    Prev
    Next
    INDEX
    Explanations

    seeking clarification

    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
    </b>
    -1.58
     provocar
    -1.58
     try
    -1.57
     are
    -1.54
     temos
    -1.52
     "
    -1.46
     podem
    -1.45
     like
    -1.45
     такие
    -1.42
    -
    -1.41
    POSITIVE LOGITS
    although
    2.02
    0
    1.85
    but
    1.80
    though
    1.75
    vereignty
    1.73
     استفاده
    1.73
    and
    1.65
    龗
    1.64
    ens
    1.63
    lizing
    1.63
    Activations Density 0.037%

    No Known Activations