© 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. 75984
    Prev
    Next
    INDEX
    Explanations

    URL paths and function calls

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

    The neuron strongly activates on numeric tokens (digits and digit sequences, including version‐style numbers and section numbers).

    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
    (?:
    -0.69
    ––––
    -0.65
    arda
    -0.65
     alone
    -0.65
     SLO
    -0.64
    ってない
    -0.64
     discriminated
    -0.64
    styl
    -0.63
     受
    -0.63
    億円
    -0.63
    POSITIVE LOGITS
     kinase
    0.72
     graces
    0.70
    mouseout
    0.68
    QUIS
    0.65
    ベルト
    0.64
    Lind
    0.64
     Auschwitz
    0.63
     статистика
    0.63
    getEnd
    0.62
    WICK
    0.61
    Activations Density 0.068%

    No Known Activations