© 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. 9639
    Prev
    Next
    INDEX
    Explanations

    a [adjective/noun]

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

    The neuron is looking for numeric tokens that include a decimal point (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
    :
    0.73
    Leaks
    0.62
    zens
    0.60
    leden
    0.60
    Unknown
    0.58
    ;
    0.57
    This
    0.56
    Enc
    0.56
    !
    0.56
    UT
    0.55
    POSITIVE LOGITS
     voyage
    0.66
     humorous
    0.64
     meditative
    0.61
     experiential
    0.61
     communicative
    0.61
     discursive
    0.61
     quei
    0.60
     contemplative
    0.60
     matroid
    0.59
     normative
    0.59
    Activations Density 0.003%

    No Known Activations