© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 107503
    Prev
    Next
    INDEX
    Explanations

    court decided dates

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

    This neuron activates mainly on numeric literals (number tokens) 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
    ometric
    -0.74
     Bibliography
    -0.73
    RelativeLayout
    -0.73
    ระ
    -0.70
    の小
    -0.69
    טי
    -0.69
    成本
    -0.68
    apd
    -0.68
    AutoSize
    -0.68
     Majesté
    -0.67
    POSITIVE LOGITS
     Shakes
    0.69
    vimos
    0.67
     Vauxhall
    0.65
     fancied
    0.65
     reprint
    0.65
     ਨੂੰ
    0.64
     sambung
    0.64
     Osna
    0.63
    Pener
    0.63
     overcoming
    0.63
    Activations Density 0.052%

    No Known Activations