© 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. 552
    Prev
    Next
    INDEX
    Explanations

    providing instructions or information

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

    The neuron strongly fires on words and phrases that express the act of searching or finding (e.g. “find,” “search for,” “finding”).

    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
    Contents
    0.29
    としての
    0.28
    なども
    0.28
    Progress
    0.27
    上の
    0.27
    '
    0.27
    を残
    0.27
    Text
    0.26
    lina
    0.26
    。
    0.26
    POSITIVE LOGITS
     подходя
    0.53
     an
    0.49
     suitable
    0.49
     a
    0.47
     replacements
    0.46
     something
    0.45
     μια
    0.44
     geeign
    0.44
    了一個
    0.44
    合适的
    0.44
    Activations Density 0.740%

    No Known Activations