© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 69032
    Prev
    Next
    INDEX
    Explanations

    code parsing and generation

    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
    ‟
    -1.38
    得太
    -1.23
    for
    -1.20
    resulting
    -1.19
    Zubereitung
    -1.18
     disregard
    -1.17
    Descriere
    -1.16
    ↵↵
    -1.14
     kulak
    -1.14
    ush
    -1.13
    POSITIVE LOGITS
     their
    1.73
     of
    1.34
     an
    1.19
     kegiatan
    1.17
     at
    1.17
     when
    1.16
     to
    1.12
    ЕВ
    1.10
     what
    1.09
     a
    1.09
    Activations Density 0.003%

    No Known Activations