© 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. 11785
    Prev
    Next
    INDEX
    Explanations

    Boolean flag, hyphen, 0, fut

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

    The neuron spikes on unusually rare or distinctive single tokens (proper names, pronouns, or other low‐frequency “content” words) rather than on common words.

    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
    ോ
    0.77
    Sch
    0.74
    Pl
    0.73
    st
    0.73
    ona
    0.71
    ш
    0.71
    az
    0.69
     ఘ
    0.69
    ii
    0.68
    пла
    0.68
    POSITIVE LOGITS
     Godzilla
    0.98
     psychopath
    0.95
     Omicron
    0.94
     empê
    0.93
     homeopathy
    0.93
     influencer
    0.93
     Meghan
    0.90
     dirige
    0.89
     Obstetrics
    0.89
     disinfectant
    0.88
    Activations Density 0.000%

    No Known Activations