© 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. 6110
    Prev
    Next
    INDEX
    Explanations

    stories about exhaustion or movies

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

    This neuron activates on capitalized multiword phrases typical of book or article titles.

    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
    ō
    0.56
     of
    0.50
    ؛
    0.49
    ;
    0.48
    .
    0.48
    ،
    0.46
     médico
    0.46
     ز
    0.44
    ár
    0.43
    ſ
    0.43
    POSITIVE LOGITS
     Fleurit
    0.58
     +/-
    0.55
    こんな
    0.52
    晠
    0.52
    ታል
    0.50
    +/-
    0.49
     oops
    0.48
    খেজুর
    0.48
     mindless
    0.48
    কাঁ
    0.47
    Activations Density 0.018%

    No Known Activations