© 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. 130365
    Prev
    Next
    INDEX
    Explanations

    questions about sources

    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
    recently
    -1.41
    several
    -1.38
     hunne
    -1.31
     большинство
    -1.30
     shou
    -1.29
     mediocre
    -1.27
     momente
    -1.27
     geene
    -1.26
    certainly
    -1.25
     poë
    -1.25
    POSITIVE LOGITS
     what
    2.28
     how
    2.09
     where
    1.68
     What
    1.68
     a
    1.64
     an
    1.64
     How
    1.59
     still
    1.52
     not
    1.51
     does
    1.49
    Activations Density 0.070%

    No Known Activations