© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 9487
    Prev
    Next
    INDEX
    Explanations

    parenthetical information

    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
    (!__
    -1.30
    ..........
    -1.19
     .......
    -1.18
     .........
    -1.14
     (!__
    -1.07
     dando
    -1.04
    還要
    -1.03
     astute
    -1.02
     ........
    -1.02
    .............
    -1.01
    POSITIVE LOGITS
     (
    1.43
    جير
    1.20
     with
    1.10
     through
    1.07
     during
    1.06
    بيل
    1.02
     Through
    0.97
     at
    0.97
     without
    0.97
     (£
    0.96
    Activations Density 0.126%

    No Known Activations