© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 65227
    Prev
    Next
    INDEX
    Explanations

    section markers and numbers

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

    The main thing this neuron does is detect multi‐digit numerical tokens (e.g. page numbers, years, volume/issue identifiers) in the text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     so
    -1.13
    <i>
    -1.05
    <b>
    -1.02
    TagMode
    -1.00
     I
    -0.99
    لم
    -0.96
     و
    -0.95
     broderie
    -0.95
    <em>
    -0.94
    so
    -0.93
    POSITIVE LOGITS
    Aufbau
    1.36
     these
    1.29
    Föld
    1.27
    مشخصات
    1.24
    Anzeige
    1.21
     навіть
    1.20
    Sprache
    1.15
    ների
    1.15
    Приготовление
    1.15
    Vorte
    1.14
    Activations Density 0.005%

    No Known Activations