© 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-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 6855
    Prev
    Next
    INDEX
    Explanations

    lists, etc

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

    The neuron fires on tokens that are part of formal numeric references or identifiers—e.g. section or clause numbers, slashes and semicolons in legal citations or technical path/spec strings.

    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_24_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
    .
    0.85
    :
    0.75
    !
    0.69
    (
    0.62
     (
    0.58
    -
    0.57
    ,
    0.56
     .
    0.55
    ak
    0.55
    And
    0.54
    POSITIVE LOGITS
     observability
    0.52
     інших
    0.52
     конструкция
    0.52
     presets
    0.50
     বাঙ্গালীর
    0.50
     বাঙ্গালীদের
    0.50
     পাকিস্তানীদের
    0.50
     efficace
    0.49
     hardness
    0.49
     tablespoons
    0.49
    Activations Density 0.195%

    No Known Activations