© 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. 9537
    Prev
    Next
    INDEX
    Explanations

    generation Alpha

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

    The neuron activates on imperative action words—i.e. verbs used as instructions or commands.

    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
    这意味着
    0.86
    春天
    0.84
     groin
    0.83
     mitigation
    0.78
    课
    0.78
    山市
    0.77
    盔
    0.76
    𝘧
    0.76
    越南
    0.76
     передба
    0.76
    POSITIVE LOGITS
     upto
    0.81
    IX
    0.71
    NN
    0.70
    BR
    0.70
    ds
    0.68
    IMENTO
    0.68
    KK
    0.68
    сы
    0.67
    BE
    0.67
    BP
    0.67
    Activations Density 0.000%

    No Known Activations