© 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. 31-GEMMASCOPE-2-RES-16K
    7. 7543
    Prev
    Next
    INDEX
    Explanations

    punctuation and formatting

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

    The neuron detects occurrences of the word “Book,” especially when used as a heading or title.

    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_31_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
    themem
    0.60
    [])
    0.59
    作家
    0.57
    頚
    0.57
    composite
    0.56
     выступления
    0.55
    toprule
    0.54
    
    0.54
     нормально
    0.53
     статті
    0.53
    POSITIVE LOGITS
     boxes
    0.60
     pumps
    0.59
     Rang
    0.59
     acres
    0.58
     edges
    0.57
     funny
    0.57
     Take
    0.56
     அதிகம்
    0.56
     skin
    0.55
     eks
    0.55
    Activations Density 0.000%

    No Known Activations