© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 58170
    Prev
    Next
    INDEX
    Explanations

    iso- followed by suffix

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

    The neuron is tuned to detect occurrences of ISO standard identifiers (tokens like “ISO-xxx”).

    oai_token-act-pair · o4-mini
    Triggered by @jyhe0408
    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
    Negative Logits
    >
    -3.02
     were
    -2.95
    渽
    -2.75
     to
    -2.69
    鲽
    -2.63
     and
    -2.59
    );
    -2.39
    ᯾
    -2.31
     terbesar
    -2.31
    $,
    -2.30
    POSITIVE LOGITS
    猻
    3.22
     was
    3.09
    犛
    2.55
    Spesifikasi
    2.50
    
    2.39
    哢
    2.36
    u
    2.33
    䊐
    2.31
     作る
    2.31
    횃
    2.28
    Activations Density 0.009%

    No Known Activations