© 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. 116062
    Prev
    Next
    INDEX
    Explanations

    facebook policies and social media

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

    This neuron activates on numeric tokens (sequences of digits).

    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
    AccessFile
    -0.83
    HexString
    -0.82
    nalités
    -0.82
    ρεσ
    -0.75
     /*#__
    -0.75
     Grund
    -0.73
     Heck
    -0.72
    ण्या
    -0.72
    颅
    -0.71
    chauffer
    -0.71
    POSITIVE LOGITS
     GraphQL
    0.95
    GraphQL
    0.77
     analogous
    0.74
    InputData
    0.73
    muta
    0.72
    ruma
    0.72
     Mercure
    0.69
    instagram
    0.69
    ينا
    0.68
    腎
    0.68
    Activations Density 0.012%

    No Known Activations