© 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. 10344
    Prev
    Next
    INDEX
    Explanations

    model prediction

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

    The neuron is activated by decimal numbers (floating-point numeric tokens) typically found in citation or reference identifiers.

    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
    الو
    0.95
    伈
    0.87
    Upp
    0.86
    𝙈
    0.84
    唏
    0.83
    France
    0.82
    Trashed
    0.81
    Apakah
    0.80
    Viewing
    0.79
    डब्ल्यू
    0.79
    POSITIVE LOGITS
    ש
    0.88
     na
    0.75
     comeback
    0.69
     Cowboys
    0.66
     Du
    0.66
    :-
    0.65
     పెట్ట
    0.63
     Libra
    0.63
     pass
    0.61
     speak
    0.61
    Activations Density 0.000%

    No Known Activations