© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 100492
    Prev
    Next
    INDEX
    Explanations

    overflow and hidden

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

    the word "overflow" in programming and technical contexts.

    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
    跸
    -1.82
     miniaturka
    -1.78
    馓
    -1.73
    蒌
    -1.70
     suministros
    -1.69
    <0x00>
    -1.60
    呶
    -1.60
     Reſ
    -1.58
     considerados
    -1.57
    became
    -1.55
    POSITIVE LOGITS
     of
    2.19
    ↵
    2.09
    s
    1.88
     can
    1.62
    for
    1.60
    7
    1.60
    e
    1.59
    8
    1.59
    b
    1.59
     also
    1.57
    Activations Density 0.035%

    No Known Activations