© 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. 24-GEMMASCOPE-2-RES-16K
    7. 12836
    Prev
    Next
    INDEX
    Explanations

    explaining processes or characteristics

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

    The neuron fires on concrete action verbs—especially those denoting directives or decisive moves (e.g. refused, cut, learn, review, pull, load, run).

    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
    0.68
    這麼
    0.64
    }$.
    0.61
    这两
    0.59
    దవ
    0.59
    .)
    0.57
    ·
    0.57
     \%$.
    0.56
    。
    0.56
     دیا۔
    0.56
    POSITIVE LOGITS
    이고
    0.95
    ですし
    0.89
     และ
    0.89
    そして
    0.86
     και
    0.86
     있고
    0.84
    এবং
    0.81
     ইত্যা
    0.80
    và
    0.79
     etc
    0.79
    Activations Density 1.535%

    No Known Activations