© 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. 91022
    Prev
    Next
    INDEX
    Explanations

    One Bread One Body

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

    The neuron activates on numeric literal tokens (e.g. version numbers, years, numeric constants) in code.

    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
    Fishing
    -0.68
    athetic
    -0.68
    Acts
    -0.66
    getic
    -0.65
     take
    -0.65
    Tome
    -0.65
    temon
    -0.65
    udz
    -0.62
    titue
    -0.62
    endis
    -0.61
    POSITIVE LOGITS
     PLO
    0.74
     guste
    0.70
     husband
    0.70
    farlane
    0.69
     TAS
    0.68
    RenderTarget
    0.67
    eless
    0.67
     Near
    0.66
    Anmerkungen
    0.66
    Prevalence
    0.66
    Activations Density 0.079%

    No Known Activations