© 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. 15344
    Prev
    Next
    INDEX
    Explanations

    pinpoint, ASM, DOMAIN

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

    This neuron consistently fires on the first substantive content token after a segment or paragraph boundary, effectively marking the start of a new text segment.

    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
    up
    0.79
     salaire
    0.79
     elettron
    0.77
    Т
    0.77
    monthly
    0.76
    ડ
    0.76
    mediated
    0.76
    ह
    0.74
    stimulated
    0.74
     carica
    0.73
    POSITIVE LOGITS
    停车场
    0.73
    ='
    0.70
     eagle
    0.70
     jacks
    0.69
    ="#"
    0.69
    のです
    0.68
    镜头
    0.67
     рэгістра
    0.65
    好事
    0.65
    备注
    0.64
    Activations Density 0.000%

    No Known Activations