© 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
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 8434
    Prev
    Next
    INDEX
    Explanations

    Final answer conclusion

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

    The neuron activates on the floating‐point score or confidence values (and their “Answer” label) that appear alongside answer entries.

    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
    ↵↵↵↵
    0.62
    </li>
    0.60
    questions
    0.60
    <{
    0.57
    ↵↵
    0.56
    ）（
    0.56
     Clauses
    0.55
     questions
    0.54
     Э
    0.54
    桌
    0.54
    POSITIVE LOGITS
     transplantation
    0.66
     conlleva
    0.64
     definitiva
    0.62
     comporta
    0.59
    संह
    0.59
     definitivo
    0.58
    スタンダード
    0.58
    ರುವುದರಿಂದ
    0.57
     එය
    0.56
    നട
    0.56
    Activations Density 0.003%

    No Known Activations