© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 13526
    Prev
    Next
    INDEX
    Explanations

    concerns, criticism, fears

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

    This neuron detects words that signal criticism, concern, or objections (e.g., “concerns,” “raised,” “critics,” “complaints”).

    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
    ,
    0.73
    eroy
    0.71
    outcome
    0.70
    ності
    0.68
     руководи
    0.68
    ime
    0.66
    Forward
    0.66
    좇
    0.66
    result
    0.65
     отношении
    0.65
    POSITIVE LOGITS
     liberalization
    0.72
     它
    0.69
     malnutrition
    0.69
     distributive
    0.67
     drawbacks
    0.67
    彡
    0.66
     使い
    0.66
    嘀
    0.66
     overflowing
    0.65
     housekeeper
    0.64
    Activations Density 0.007%

    No Known Activations