© 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. 4394
    Prev
    Next
    INDEX
    Explanations

    . (punctuation)

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

    The neuron fires most strongly on the final content word immediately preceding a segment boundary (i.e. the last token before an <end> or new block).

    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
    braith
    0.89
    𝘺
    0.89
    wallepics
    0.86
    𝘫
    0.81
    я
    0.81
     Потому
    0.80
    𝘱
    0.80
    reflectionCamera
    0.80
    onbury
    0.80
    هُ
    0.80
    POSITIVE LOGITS
    LAND
    0.73
    '
    0.71
    LC
    0.70
    KI
    0.69
     enregist
    0.68
    Machine
    0.67
    acchi
    0.67
    戦争
    0.66
    棧
    0.66
    LOC
    0.66
    Activations Density 0.000%

    No Known Activations