© 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. 31-GEMMASCOPE-2-RES-16K
    7. 336
    Prev
    Next
    INDEX
    Explanations

    selection or invention

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

    The neuron fires on tokens that are capitalized or title-case words (e.g. proper nouns, brand or product names, and sentence-initial 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_31_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
    
    0.35
    efois
    0.34
    »).
    0.34
    ولوج
    0.33
    áus
    0.33
    ногда
    0.33
    ካከል
    0.32
     creciendo
    0.32
    icoter
    0.32
     المصطلح
    0.31
    POSITIVE LOGITS
    【
    0.34
    ✨
    0.33
    Good
    0.33
    High
    0.33
    b
    0.31
    送料無料
    0.31
    L
    0.30
    !
    0.30
    👍
    0.30
    日本製
    0.30
    Activations Density 0.394%

    No Known Activations