© 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. 7447
    Prev
    Next
    INDEX
    Explanations

    counterfactuals, ELAB, Facebook, percentage, Life, Boundary

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

    The neuron fires most strongly on tokens that mark new sections or structural breaks—e.g. section numbers or labels in parentheses, headings, or the first word of a new 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
    ب
    0.97
    Alban
    0.86
    蟬
    0.85
    mari
    0.84
    ASSI
    0.82
    arxiv
    0.82
    Cread
    0.79
    ق
    0.78
    anen
    0.77
    CLASSI
    0.77
    POSITIVE LOGITS
    担心
    0.75
     helst
    0.75
     związku
    0.73
     nombre
    0.73
     появления
    0.73
     możemy
    0.72
     Каждый
    0.71
    名为
    0.71
     każdym
    0.71
    ηση
    0.70
    Activations Density 0.000%

    No Known Activations