© 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
    2. Gemma-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 6002
    Prev
    Next
    INDEX
    Explanations

    **examine plaque**

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

    This neuron fires on imperative “add” instructions (and similar command verbs) in step-by-step or tutorial language.

    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
    HLA
    0.79
    Invitrogen
    0.78
    <unused1830>
    0.76
    KAT
    0.75
     odgovor
    0.75
    Kako
    0.74
    Compatibility
    0.73
    ⟥
    0.73
    <unused2165>
    0.73
    ಭಾವ
    0.72
    POSITIVE LOGITS
     these
    0.91
     theses
    0.84
    เหล่านี้
    0.84
     destes
    0.84
     alles
    0.83
     quaisquer
    0.83
     tudo
    0.78
    这一切
    0.78
     estos
    0.77
     этих
    0.77
    Activations Density 0.162%

    No Known Activations