© 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. 10862
    Prev
    Next
    INDEX
    Explanations

    really + adjective/adverb

    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
    ⤿
    -1.64
     déplo
    -1.64
    をご覧ください
    -1.63
    ਃ
    -1.63
    Зно
    -1.60
    虯
    -1.56
    skjaer
    -1.56
    二日
    -1.53
    ꈊ
    -1.52
    褫
    -1.49
    POSITIVE LOGITS
    .
    1.88
    ↵
    1.64
     was
    1.61
    ?
    1.46
    '
    1.43
     can
    1.41
    脇
    1.38
    [
    1.35
    ...
    1.34
     særlig
    1.34
    Activations Density 0.018%

    No Known Activations