© 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. 10-GEMMASCOPE-RES-131K
    7. 123902
    Prev
    Next
    INDEX
    Explanations

    file paths and scientific names

    np_acts-logits-general · gemini-2.5-flash-lite

    backslash characters in programming code or regex patterns.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
     &
    -2.92
    菝
    -2.88
     and
    -2.83
    /
    -2.34
    ?
    -2.30
     to
    -2.16
     dejamos
    -2.14
    ).
    -2.14
     aña
    -2.03
     первый
    -1.98
    POSITIVE LOGITS
    re
    3.00
    鹇
    2.72
    鱻
    2.67
    鹚
    2.67
     pérd
    2.64
    薷
    2.64
    事は
    2.48
    鉭
    2.44
    顚
    2.44
     смог
    2.42
    Activations Density 0.001%

    No Known Activations