© 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. 5392
    Prev
    Next
    INDEX
    Explanations

    building complexities

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

    The neuron flags numeric tokens containing 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
    مون
    0.80
    ی
    0.77
    اد
    0.76
    editing
    0.75
    م
    0.74
     storey
    0.73
     participle
    0.73
    ья
    0.73
    m
    0.71
    муще
    0.71
    POSITIVE LOGITS
     giov
    0.78
     biar
    0.76
    UTER
    0.74
    ñas
    0.74
    riti
    0.74
    人大
    0.74
    ichier
    0.73
     progett
    0.72
     gioc
    0.71
     народа
    0.71
    Activations Density 0.000%

    No Known Activations