© 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. 10973
    Prev
    Next
    INDEX
    Explanations

    limerick or poem requests

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

    This neuron fires strongly on all‐caps headings or section titles (block‐leading uppercase words) in the text.

    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
     powerhouse
    0.69
     or
    0.67
    或
    0.66
     unleashed
    0.65
     Kenyatta
    0.65
     hesitant
    0.64
     curvy
    0.63
     cush
    0.62
     embroiled
    0.62
    0.61
    POSITIVE LOGITS
    _.
    0.95
    *_
    0.89
    esterday
    0.89
    Hc
    0.82
    *.
    0.82
    lii
    0.77
    клары
    0.77
    (_
    0.77
     interesantes
    0.77
    rfc
    0.77
    Activations Density 0.008%

    No Known Activations