© 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. 31-GEMMASCOPE-2-RES-16K
    4. 15974
    Prev
    Next
    INDEX
    Explanations

    to replenish

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

    The neuron fires on procedural “how‐to” or instructional language—i.e. text giving technical instructions or directions.

    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_31_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
     लेगा
    0.37
    있다
    0.35
    ",
    0.35
    C
    0.35
    или
    0.35
    wani
    0.34
    with
    0.34
     Daniels
    0.33
    成立于
    0.32
    ?
    0.32
    POSITIVE LOGITS
     fiancé
    0.39
    ूले
    0.39
     forego
    0.38
     useEffect
    0.37
     adhere
    0.37
     prioritise
    0.36
    டுகளில்
    0.36
     покра
    0.36
     forgo
    0.35
    ển
    0.35
    Activations Density 0.017%

    No Known Activations