© 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. 129
    Prev
    Next
    INDEX
    Explanations

    hexadecimal prefixes and numbers

    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
     last
    -1.30
     Hinsicht
    -1.15
    Kommentare
    -1.13
     soon
    -1.11
    Präsident
    -1.09
    Zubereitung
    -1.09
    oprene
    -1.05
    メリット
    -1.04
     στρα
    -1.04
    kanı
    -1.03
    POSITIVE LOGITS
    .
    1.44
    ↵
    1.13
    !
    1.13
    "
    1.03
    “
    1.02
    )
    0.97
    ;
    0.96
    ビーム
    0.94
     Cancun
    0.94
     Juillet
    0.92
    Activations Density 0.003%

    No Known Activations