© 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. 129550
    Prev
    Next
    INDEX
    Explanations

    ... is a placeholder

    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
     aquello
    -1.63
     réve
    -1.60
    蘩
    -1.59
     récol
    -1.58
     véhic
    -1.55
     refroid
    -1.53
    튿
    -1.50
    besondere
    -1.48
    豨
    -1.45
     gouttes
    -1.42
    POSITIVE LOGITS
     would
    2.22
     by
    2.19
     then
    2.14
     when
    2.11
     is
    1.99
     just
    1.98
     can
    1.94
     as
    1.94
     still
    1.93
     from
    1.83
    Activations Density 0.008%

    No Known Activations