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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 13556
    Prev
    Next
    INDEX
    Explanations

    deleterious condition

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

    names of software, programming libraries, and technical frameworks.

    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
     ominous
    -2.52
    on
    -2.38
    ౭
    -2.38
    蹰
    -2.38
     conocidas
    -2.27
    ﮟ
    -2.27
    ౩
    -2.17
     aceites
    -2.14
    rdoba
    -2.14
    of
    -2.13
    POSITIVE LOGITS
    ↵
    3.45
    .
    2.69
     of
    2.36
     регулярно
    2.20
    总会
    2.16
     vollständige
    2.11
    2
    2.09
     slechts
    2.08
    ’;
    2.02
     тщательно
    2.02
    Activations Density 0.001%

    No Known Activations