© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 14669
    Prev
    Next
    INDEX
    Explanations

    cancelled plans, necessary, typically have

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

    The neuron is keyed to sentence- or section-initial tokens—discourse markers and words that open or shift to a new sentence or paragraph.

    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
    Metadata
    0.78
    Container
    0.73
    Raw
    0.70
    Distributed
    0.70
    t
    0.68
    //#
    0.67
    Remainder
    0.66
    CENTER
    0.66
     কর্মরত
    0.66
    _
    0.66
    POSITIVE LOGITS
     feste
    0.86
    턱
    0.84
     spans
    0.80
    ミー
    0.79
     เลือก
    0.79
     concedes
    0.79
     stature
    0.79
     doping
    0.78
     descanso
    0.78
     stadiums
    0.78
    Activations Density 0.000%

    No Known Activations