© 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. 16231
    Prev
    Next
    INDEX
    Explanations

    explanation of concepts

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

    The neuron selectively fires on longer, content-heavy (i.e. relatively rare or semantically rich) words rather than on common short 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
     slipped
    0.94
     }}$
    0.92
     lagged
    0.84
    찮
    0.83
     состоя
    0.79
    рованное
    0.76
    ATE
    0.75
     ripped
    0.75
     departed
    0.75
     warped
    0.75
    POSITIVE LOGITS
     accords
    0.81
    しば
    0.77
    َر
    0.77
    غب
    0.77
     phương
    0.76
     Cuenta
    0.75
     Indones
    0.74
     dây
    0.73
    َس
    0.73
     cuentas
    0.72
    Activations Density 0.000%

    No Known Activations