© 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. 1581
    Prev
    Next
    INDEX
    Explanations

    previous or following

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

    The neuron fires on dynamic storytelling words—especially sequences of action verbs and emphasizing adverbs (coming, went, defend, told, even, further, again) that advance or intensify a narrated event.

    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
    1.16
     +
    1.13
     /
    0.98
    +
    0.98
     &
    0.97
     (
    0.95
     typically
    0.93
     ≥
    0.89
     potentially
    0.88
     increasingly
    0.88
    POSITIVE LOGITS
     Alhaji
    1.20
     Comrade
    1.12
     اصلا
    1.11
     Kaduna
    1.11
     Abia
    1.11
     Jumat
    1.09
     musul
    1.09
     Sachen
    1.09
     dilapidated
    1.06
     Enugu
    1.05
    Activations Density 0.570%

    No Known Activations