© 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. 1792
    Prev
    Next
    INDEX
    Explanations

    turning into

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

    The neuron fires on uppercase alphanumeric codes or abbreviations (e.g. currency symbols, company tickers, hex color codes).

    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
     wówczas
    0.63
    闗
    0.60
     LANGUAGES
    0.60
     INFORMATION
    0.59
     ইনস্টি
    0.59
     kerap
    0.59
     náz
    0.58
    诒
    0.58
     Vire
    0.57
     ADMINISTRATION
    0.57
    POSITIVE LOGITS
     in
    0.76
    '
    0.64
    chan
    0.63
    itm
    0.58
     which
    0.58
    igas
    0.57
    ᐈ
    0.57
     into
    0.57
     în
    0.57
    ächlich
    0.57
    Activations Density 0.000%

    No Known Activations