© 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. 14284
    Prev
    Next
    INDEX
    Explanations

    dropdown menu

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

    The neuron fires most strongly on mid‐sentence “pivot” words—i.e. common discourse/action tokens like open, because, disclaim, dropdown, higher, month—that signal shifts or key steps in an explanation.

    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
     americanos
    0.94
     europeos
    0.89
     염
    0.88
     jiné
    0.86
     뮤
    0.83
     وفي
    0.82
     sleepless
    0.82
     amperes
    0.80
     연
    0.80
    ベージュ
    0.80
    POSITIVE LOGITS
    enal
    0.84
    ib
    0.80
    GA
    0.75
    en
    0.73
    nuxt
    0.70
    version
    0.69
    ጠበ
    0.69
    ുടെ
    0.68
    onomy
    0.68
    agency
    0.68
    Activations Density 0.001%

    No Known Activations