© 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. 12422
    Prev
    Next
    INDEX
    Explanations

    socat and llamaIndex

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

    This neuron fires strongly on the final token of each text segment, marking the end 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
    Arthur
    0.79
    2
    0.75
    Richard
    0.74
    4
    0.73
    3
    0.71
    M
    0.67
    David
    0.67
    Paul
    0.66
    John
    0.66
    G
    0.66
    POSITIVE LOGITS
     określ
    0.72
     caut
    0.69
     negated
    0.64
     geeign
    0.64
     solutes
    0.64
     sinon
    0.64
     analyte
    0.63
    欹
    0.63
     beho
    0.63
     irgend
    0.62
    Activations Density 0.001%

    No Known Activations