© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 66812
    Prev
    Next
    INDEX
    Explanations

    parts sections chapters numbering

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

    This neuron identifies structural document headings and labels—like section/part/chapter numbers or roman numerals.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     and
    -1.15
     from
    -1.15
     since
    -1.03
     нашим
    -0.99
     mohli
    -0.98
    糅
    -0.98
     at
    -0.96
     when
    -0.95
    hyundai
    -0.94
     including
    -0.93
    POSITIVE LOGITS
    section
    1.16
     "}";
    1.02
    verture
    1.02
     только
    1.02
    для
    0.99
    }}_
    0.98
    ubit
    0.98
    tainen
    0.97
    ؤية
    0.97
     المتح
    0.97
    Activations Density 0.017%

    No Known Activations