© 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
    2. Gemma-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 3018
    Prev
    Next
    INDEX
    Explanations

    money, points, advantages, or costs

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

    This neuron fires strongly on content words that end a sentence or clause—i.e. the final substantive word just before the punctuation.

    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
     your
    0.55
     enthr
    0.49
    의
    0.49
     heartbeat
    0.49
    为您
    0.49
     pulsating
    0.48
     shutdown
    0.47
     ambience
    0.47
     remedy
    0.47
     smother
    0.47
    POSITIVE LOGITS
     Nhưng
    0.81
    但我
    0.78
     لكن
    0.75
     אבל
    0.75
    但他
    0.74
     근데
    0.73
     但
    0.72
    เพราะ
    0.72
     하지만
    0.71
    但
    0.71
    Activations Density 0.000%

    No Known Activations