© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 100142
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and code

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

    single digit numbers, especially when they appear at the beginning of lines or in structured numeric contexts like legal citations, code, and data tables.

    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
     the
    -3.59
     '
    -2.78
     recibe
    -2.28
    ।
    -2.25
     a
    -2.20
    ︲
    -2.11
    mainly
    -2.09
    ‐
    -2.08
     acclaimed
    -2.05
     replete
    -2.02
    POSITIVE LOGITS
     When
    2.41
    There
    2.41
     There
    2.38
    They
    2.34
    鴟
    2.31
    เหมือน
    2.30
    Creating
    2.25
    {
    2.23
    中国的
    2.23
    When
    2.17
    Activations Density 0.074%

    No Known Activations