© 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. 10-GEMMASCOPE-RES-131K
    7. 104687
    Prev
    Next
    INDEX
    Explanations

    \mathbb{R}, \epsilon, \delta, \emptyset

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

    The neuron activates on numeric constants (including digits, decimals, and numbers in math‐mode tokens).

    oai_token-act-pair · o4-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    [
    -1.66
    mathrm
    -1.62
    -
    -1.60
    </b>
    -1.55
    逦
    -1.53
    -“
    -1.45
    齶
    -1.45
    actéristi
    -1.42
    ”.
    -1.40
    糧
    -1.40
    POSITIVE LOGITS
    𐑂
    1.70
     that
    1.64
     perubahan
    1.64
    𖧷
    1.63
    ABILIDAD
    1.59
     bukti
    1.57
    Composición
    1.57
     liburan
    1.57
    wakili
    1.56
     paisajes
    1.54
    Activations Density 0.015%

    No Known Activations