© 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. 6841
    Prev
    Next
    INDEX
    Explanations

    Author metadata

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

    The neuron spikes on rarer, polysyllabic content words (longer nouns, adjectives, and modals) rather than on common function 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
    loten
    0.81
    س
    0.80
     jLabel
    0.76
    𝑠
    0.75
    }]=
    0.75
    geschossiges
    0.75
    ∶
    0.74
    እና
    0.73
    中断
    0.71
    𝑟
    0.71
    POSITIVE LOGITS
    end
    0.73
    op
    0.71
    ian
    0.71
    вается
    0.71
     dobrze
    0.70
    ायत
    0.69
    usnya
    0.69
    uksen
    0.67
    lly
    0.67
    addling
    0.66
    Activations Density 0.001%

    No Known Activations