© 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. 12418
    Prev
    Next
    INDEX
    Explanations

    compare the price with

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

    The neuron strongly activates on the first substantive tokens of new segments or sentences (i.e. sentence-initial, often capitalized words).

    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
    ли
    0.87
    ты
    0.82
    𝕟
    0.80
    сси
    0.80
    τε
    0.78
    డి
    0.78
     grievous
    0.77
    ñ
    0.77
    ры
    0.76
    нить
    0.76
    POSITIVE LOGITS
    াদার
    0.79
    ليب
    0.76
    踝
    0.75
    anske
    0.72
     Datenschutz
    0.70
    itional
    0.70
    ER
    0.70
    onic
    0.70
     Rotary
    0.69
     togetherness
    0.68
    Activations Density 0.000%

    No Known Activations