© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 8769
    Prev
    Next
    INDEX
    Explanations

    story telling, voice, single person, desired quality, country

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

    The neuron activates on numeric tokens that include decimal points (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
     participating
    0.79
    sst
    0.75
    ה
    0.73
    sam
    0.73
    sr
    0.72
     Fossil
    0.72
    sit
    0.70
     pessimistic
    0.69
    {{\
    0.68
    s
    0.68
    POSITIVE LOGITS
    على
    0.90
     fluxo
    0.86
     Muitos
    0.86
    iete
    0.84
    केंसी
    0.83
    cluso
    0.82
    كل
    0.82
    plet
    0.81
    klı
    0.80
     Євро
    0.80
    Activations Density 0.000%

    No Known Activations