© 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. 1295
    Prev
    Next
    INDEX
    Explanations

    code block syntax elements

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

    The neuron activates on floating‐point numeric literals (decimal 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
    ości
    0.59
    snd
    0.55
     Poirot
    0.55
    )
    0.54
     FGD
    0.53
    Chim
    0.52
    )">
    0.52
    )?.
    0.52
     publie
    0.52
    போது
    0.51
    POSITIVE LOGITS
    ار
    0.66
    は
    0.64
     tieto
    0.62
     kapsamında
    0.62
     as
    0.61
    <unused2174>
    0.60
    eneration
    0.59
     ও
    0.57
    中的
    0.56
     dailySales
    0.56
    Activations Density 0.001%

    No Known Activations