© 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. 118773
    Prev
    Next
    INDEX
    Explanations

    code file names

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

    opening brackets (square brackets `[`) in code or structured data, particularly in array declarations and JSON structures.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    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
     or
    -2.13
     When
    -1.49
     Since
    -1.41
    just
    -1.38
    as
    -1.34
    In
    -1.34
     или
    -1.33
    '
    -1.33
    Just
    -1.30
    We
    -1.30
    POSITIVE LOGITS
    ㈰
    1.35
    Ꮘ
    1.34
     contempla
    1.34
    …(
    1.33
    etui
    1.32
     prohi
    1.31
    鱨
    1.29
     crea
    1.28
    罴
    1.27
    varies
    1.27
    Activations Density 0.100%

    No Known Activations