© 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. 8831
    Prev
    Next
    INDEX
    Explanations

    adjustment, auxiliary, require, eggs, formal, negative, heat, legally

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

    The neuron responds to numerical measurements, quantities, and related technical terms (e.g., numbers, units, and quantifiable details).

    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
     Meskipun
    0.78
    Whilst
    0.73
    Pada
    0.73
    🍱
    0.70
    🛀
    0.68
     Fakat
    0.67
     Така
    0.67
     Whilst
    0.66
    ホワイト
    0.66
    🍚
    0.66
    POSITIVE LOGITS
     successive
    0.76
     legislatures
    0.76
     yrs
    0.74
     निवडणु
    0.69
     citizenship
    0.69
     sects
    0.69
     constitutions
    0.68
     legis
    0.68
    pectives
    0.67
     citizenry
    0.67
    Activations Density 0.168%

    No Known Activations