© 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. 26392
    Prev
    Next
    INDEX
    Explanations

    action with subsequent context

    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
    などは
    -1.66
     
    -1.44
    <bos>
    -1.38
     is
    -1.35
     because
    -1.26
    chtenstein
    -1.26
    这也
    -1.22
    但是在
    -1.22
     totalité
    -1.21
     after
    -1.16
    POSITIVE LOGITS
     wspania
    1.71
     śnie
    1.68
     estadounid
    1.63
     the
    1.63
     zimowe
    1.59
    ほら
    1.57
    喁
    1.57
     chaude
    1.57
    あぁ
    1.54
     naprawdę
    1.52
    Activations Density 0.079%

    No Known Activations