© 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. 31-GEMMASCOPE-2-RES-16K
    7. 10302
    Prev
    Next
    INDEX
    Explanations

    prefixes forming words

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

    This neuron detects numeric tokens representing floating-point values (numbers with decimal points).

    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_31_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
    0.39
    -
    0.38
    M
    0.36
    Cl
    0.36
    C
    0.35
    Am
    0.35
    Ar
    0.34
    4
    0.34
    s
    0.34
    H
    0.34
    POSITIVE LOGITS
     panicked
    0.34
     grungy
    0.34
     bullpen
    0.33
     adenovirus
    0.33
     angiogenic
    0.33
     arrhyth
    0.33
     pluripotent
    0.33
     sciatica
    0.33
     एक्सरसा
    0.33
     epitopes
    0.32
    Activations Density 0.104%

    No Known Activations