© 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. 24-GEMMASCOPE-2-RES-16K
    7. 1225
    Prev
    Next
    INDEX
    Explanations

    various categories listed

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

    The neuron fires specifically on numeric tokens representing decimal‐point measurements (i.e. floating‐point 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_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
     этой
    0.62
     này
    0.58
    ;'
    0.58
    cparam
    0.57
     этом
    0.55
    ।'
    0.55
    ;'>
    0.54
     summand
    0.54
    десь
    0.54
     apud
    0.53
    POSITIVE LOGITS
     S
    0.65
     F
    0.63
     P
    0.63
     B
    0.63
     Β
    0.63
     M
    0.62
     G
    0.61
     D
    0.59
     L
    0.59
     Islamic
    0.59
    Activations Density 0.014%

    No Known Activations