© 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. 6821
    Prev
    Next
    INDEX
    Explanations

    HTML title tags

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

    This neuron primarily fires on numeric tokens (e.g., citations, figures, and other numbers).

    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
     વો
    0.55
     setCount
    0.54
     traverses
    0.53
     />;
    0.52
     traverse
    0.51
     visibility
    0.50
     ont
    0.48
    ziemy
    0.48
     テ
    0.48
     कोऑ
    0.47
    POSITIVE LOGITS
     გამოყენ
    0.56
    glightbox
    0.53
     confining
    0.52
     antigo
    0.52
     alam
    0.50
    heon
    0.50
    Mileage
    0.50
     acumin
    0.50
    抬
    0.50
     dua
    0.49
    Activations Density 0.002%

    No Known Activations