© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 15401
    Prev
    Next
    INDEX
    Explanations

    commands and actions

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

    This neuron activates on numeric tokens (digits and number words) and references to random values—i.e. numeric literals and number-related terms.

    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
    L
    0.80
    :
    0.60
    I
    0.57
    Л
    0.56
    V
    0.54
    T
    0.54
    <strong>
    0.53
    pair
    0.53
    Ø
    0.52
    C
    0.52
    POSITIVE LOGITS
    ंबकीय
    0.68
     крае
    0.66
    ziała
    0.65
     ankaŭ
    0.64
     rangi
    0.64
     kalangan
    0.64
     અન્ય
    0.64
     carrito
    0.64
    ätte
    0.63
     społ
    0.63
    Activations Density 0.010%

    No Known Activations