© 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. 12245
    Prev
    Next
    INDEX
    Explanations

    rendering text, caching

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

    The neuron strongly fires on longer, content‐bearing (and thus relatively rare) tokens—e.g. multi-syllabic or technical words rather than common function words.

    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
     bra
    0.70
    א
    0.70
    cient
    0.66
     î
    0.64
    gif
    0.63
     tutti
    0.63
    фта
    0.63
    bra
    0.63
    src
    0.62
     або
    0.62
    POSITIVE LOGITS
    చిన
    0.87
    おか
    0.86
    鳴
    0.84
    ställ
    0.83
    嗄
    0.83
    変わ
    0.81
    琿
    0.80
    湎
    0.79
     statunitense
    0.77
    常に
    0.77
    Activations Density 0.000%

    No Known Activations