© 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. 45375
    Prev
    Next
    INDEX
    Explanations

    Sprintcar ace, Championship Car, Bill Ferris

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

    The neuron strongly fires on numeric and all‐caps tokens—e.g. years, statistics, acronyms, and other digit- or uppercase-heavy fragments.

    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
    pheus
    -0.96
     Deriv
    -0.79
    Deriv
    -0.74
    estrel
    -0.73
    sburg
    -0.73
     Hillsborough
    -0.73
    Suomen
    -0.71
     modest
    -0.71
     Nasdaq
    -0.71
     NAS
    -0.70
    POSITIVE LOGITS
     sprint
    1.13
     Sprint
    0.88
    sprint
    0.83
     alcohol
    0.79
     methanol
    0.79
    alcohol
    0.79
    JECTION
    0.77
     Reading
    0.77
    carte
    0.74
     SPR
    0.74
    Activations Density 0.020%

    No Known Activations