© 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. 12207
    Prev
    Next
    INDEX
    Explanations

    master, common, pairwise, row, considered

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

    This neuron consistently lights up on relatively rare, content-heavy words—especially longer descriptive or thematic terms—marking them as semantically salient.

    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
    یس
    0.84
    策划
    0.83
     pantai
    0.80
    𝗹
    0.80
     trout
    0.78
    𝗶
    0.77
    𝗙
    0.75
    ϋ
    0.75
     sperm
    0.73
     Sorrent
    0.73
    POSITIVE LOGITS
    diag
    0.81
     قاس
    0.71
     occupations
    0.68
     occupant
    0.68
    사람
    0.68
     recog
    0.68
     kendisine
    0.68
     entitlement
    0.66
     auquel
    0.66
    спек
    0.66
    Activations Density 0.000%

    No Known Activations