© 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. 34-GEMMASCOPE-RES-131K
    7. 63678
    Prev
    Next
    INDEX
    Explanations

    legal citations and formatting

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

    The neuron strongly activates on multi‐digit numeric tokens (e.g. long numbers, years, reference IDs).

    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
    ︎
    -0.75
    PING
    -0.70
     PIN
    -0.69
    يميديا
    -0.68
     Lilly
    -0.68
     semiconductor
    -0.67
     jackpot
    -0.66
    writeString
    -0.66
    Muta
    -0.66
    Bibliographie
    -0.65
    POSITIVE LOGITS
     Palau
    0.75
     notar
    0.68
    ikor
    0.68
    瀉
    0.65
    pruchs
    0.65
    źć
    0.65
    HOUR
    0.65
    loyal
    0.64
     Peers
    0.64
    ྫ
    0.63
    Activations Density 0.052%

    No Known Activations