© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 12733
    Prev
    Next
    INDEX
    Explanations

    rule of thumb

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

    The neuron detects mentions of “Rule of …,” i.e. occurrences of the phrase “rule of” (often followed by a number or “thumb”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    teams
    0.70
    tiempo
    0.63
    सबसे
    0.61
    task
    0.61
    timeLeft
    0.60
    TIMESTAMP
    0.60
     equipos
    0.59
    ഖ
    0.59
    dec
    0.59
    TASK
    0.59
    POSITIVE LOGITS
     Abilities
    0.63
     profiled
    0.59
    ೇಖ
    0.58
     Prom
    0.58
     researched
    0.57
     said
    0.56
     Profiles
    0.56
     Waterproof
    0.56
     Henson
    0.56
     Sauv
    0.56
    Activations Density 0.001%

    No Known Activations