© 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. 307
    Prev
    Next
    INDEX
    Explanations

    book titles and authors

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

    The neuron fires on tokens that are part of bibliographic headings or titles (e.g. title words and their separating punctuation like colons).

    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
    ,
    0.26
     any
    0.21
    .
    0.21
    ?
    0.19
     freaking
    0.19
     either
    0.19
    廝
    0.19
     overly
    0.18
     solely
    0.18
     appreciable
    0.18
    POSITIVE LOGITS
    ⨔
    0.26
    ujjati
    0.26
     Система
    0.25
    <unused1670>
    0.25
    ະພັນ
    0.25
    <unused210>
    0.25
     Крем
    0.24
    iduría
    0.24
    墘
    0.24
     Кара
    0.24
    Activations Density 0.438%

    No Known Activations