© 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
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 16143
    Prev
    Next
    INDEX
    Explanations

    is the

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

    The neuron fires on definitional or explanatory phrases—especially constructions like “this is …” or “what is …” that introduce a description or definition.

    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
    .',
    0.67
    \",
    0.65
     provoque
    0.64
     („
    0.63
     grinning
    0.63
     tłumac
    0.63
    .</
    0.61
    .\\
    0.61
    \">
    0.61
     সুদর্শন
    0.61
    POSITIVE LOGITS
    사업
    0.68
     عمر
    0.64
    lomer
    0.64
    ौर
    0.63
     उम्र
    0.63
     사업
    0.63
    λα
    0.62
    markt
    0.61
    事業
    0.61
    នូវ
    0.61
    Activations Density 0.000%

    No Known Activations