© 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. 15205
    Prev
    Next
    INDEX
    Explanations

    General topics with specific examples

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

    The neuron fires strongly on the single key content word that ends a sentence or instruction step.

    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
    шення
    0.79
    ಣ
    0.77
    нди
    0.73
    isVideo
    0.69
    pare
    0.68
    vasive
    0.68
     відбувається
    0.68
    ন
    0.67
    ুকে
    0.66
    tiles
    0.66
    POSITIVE LOGITS
     Kopf
    0.77
     durchschnitt
    0.77
     podido
    0.76
     Autoren
    0.76
     Behold
    0.76
     feral
    0.75
     arisen
    0.75
     Lebens
    0.74
     Blackpool
    0.74
     Hälfte
    0.73
    Activations Density 0.000%

    No Known Activations