© 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. 10838
    Prev
    Next
    INDEX
    Explanations

    suggest alternative activity

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

    This neuron flags contentful nouns and verbs typical of formal, legal-oriented or business-style prose.

    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
    För
    0.75
    Tenemos
    0.71
    Balls
    0.71
     নিয়েছে
    0.70
    િલ્
    0.68
    ডেল
    0.68
    เ
    0.68
    ๙
    0.66
    Dent
    0.65
    Это
    0.65
    POSITIVE LOGITS
     desi
    0.95
    irat
    0.94
    lardan
    0.87
     strategi
    0.85
    leni
    0.82
    sq
    0.77
    টিআই
    0.77
     sanctity
    0.77
    si
    0.75
    lé
    0.75
    Activations Density 0.000%

    No Known Activations