© 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. 22-GEMMASCOPE-RES-131K
    7. 38881
    Prev
    Next
    INDEX
    Explanations

    Category titles

    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
    berra
    -1.56
    aneity
    -1.47
    (=)
    -1.46
    licante
    -1.35
    __:
    -1.34
    preneurs
    -1.34
    /__
    -1.30
     vermel
    -1.27
     Commentaires
    -1.22
    dienne
    -1.21
    POSITIVE LOGITS
     how
    1.54
     Mostly
    1.30
     or
    1.26
    してた
    1.23
     for
    1.22
    地域の
    1.19
     after
    1.17
     featuring
    1.15
     loosely
    1.15
     gets
    1.14
    Activations Density 0.507%

    No Known Activations