© 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. 13887
    Prev
    Next
    INDEX
    Explanations

    lists containing mixed contents

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

    This neuron fires most strongly on the last content word before each segment boundary, i.e. it detects the final token of a passage.

    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
    '
    0.84
    le
    0.76
    as
    0.75
    h
    0.74
    SOL
    0.73
    la
    0.72
    SH
    0.71
    0.70
    난
    0.70
    ме
    0.69
    POSITIVE LOGITS
     fatally
    0.92
     تمام
    0.90
     ataques
    0.86
     perju
    0.84
    礴
    0.83
    ร์
    0.79
    giraffe
    0.79
     امر
    0.78
     হামলা
    0.77
     силы
    0.77
    Activations Density 0.000%

    No Known Activations