© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 60778
    Prev
    Next
    INDEX
    Explanations

    specific dates or rates

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

    The neuron fires on dense, list-style passages that enumerate dates, numbers, and specific features—e.g. detailed schedules, event or product specification sections.

    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
     Landschafts
    -0.73
     Radford
    -0.73
     Albion
    -0.73
    reasonable
    -0.70
    erty
    -0.69
    Retro
    -0.69
    posting
    -0.68
    cieron
    -0.68
    resized
    -0.67
    ublik
    -0.67
    POSITIVE LOGITS
     modos
    0.95
     INTERESAR
    0.89
    графії
    0.88
    dehy
    0.88
     proceed
    0.87
    話は
    0.83
    cciale
    0.82
     متعلقه
    0.82
     proceeded
    0.80
     immortality
    0.80
    Activations Density 0.011%

    No Known Activations