© 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. 11693
    Prev
    Next
    INDEX
    Explanations

    carries over

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

    The neuron fires strongly on stray single‐letter or similarly rare tokens—e.g. footnote markers, isolated letters, or numeric/citation tokens.

    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
     CRUIS
    0.87
     sauvegard
    0.85
     長袖
    0.84
     ग्लूको
    0.83
     glomerular
    0.83
     acque
    0.80
    钢
    0.79
    PARAMETERS
    0.79
     perfettamente
    0.78
     compris
    0.78
    POSITIVE LOGITS
    EEN
    0.71
     Bakan
    0.70
     such
    0.67
    )))
    0.67
    );
    0.66
     genoemd
    0.65
    OU
    0.64
     co
    0.64
    ı
    0.64
    нами
    0.63
    Activations Density 0.000%

    No Known Activations