© 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. 81453
    Prev
    Next
    INDEX
    Explanations

    author: then names

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

    The neuron activates on numeric tokens—i.e. any standalone digits or number sequences.

    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
     sexuelle
    -0.70
     Invalid
    -0.69
     î
    -0.69
     помогают
    -0.68
     Inf
    -0.68
     nitrate
    -0.67
    LOGOUT
    -0.67
     Gu
    -0.67
     interrupt
    -0.66
     engineers
    -0.66
    POSITIVE LOGITS
    upassen
    0.80
    Johannes
    0.74
     CITES
    0.68
    removeAll
    0.67
     ہی
    0.66
    Дмитрий
    0.66
     Embal
    0.64
     Tees
    0.64
    IDER
    0.63
    buscar
    0.63
    Activations Density 0.064%

    No Known Activations