© 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. 74198
    Prev
    Next
    INDEX
    Explanations

    definition follows name

    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
     it
    -2.89
     Since
    -2.77
     this
    -2.59
     if
    -2.41
     your
    -2.38
     While
    -2.27
     However
    -2.23
     Despite
    -2.17
     these
    -2.14
     During
    -2.14
    POSITIVE LOGITS
     tratamientos
    1.83
    ↵↵
    1.77
     mooi
    1.76
     baumwolle
    1.75
     diseños
    1.73
     électro
    1.73
    ositol
    1.71
     spektak
    1.69
    pictures
    1.68
     PROTEIN
    1.68
    Activations Density 0.064%

    No Known Activations