© 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
    2. Gemma-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 14319
    Prev
    Next
    INDEX
    Explanations

    from scratch

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

    The neuron strongly fires on tokens that are proper names or numeric identifiers—e.g. personal/place names, years, citation numbers, question labels, times—i.e. named entities and numbers.

    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
    ಕ
    1.06
    ل
    0.91
    어
    0.85
    서
    0.84
    z
    0.82
    エ
    0.80
    רא
    0.79
    d
    0.75
    ك
    0.75
    아
    0.74
    POSITIVE LOGITS
     terpen
    0.96
     praktisch
    0.92
     frescas
    0.90
     организм
    0.89
    ColorLegend
    0.88
     поднима
    0.87
     благодаря
    0.87
     micelles
    0.86
    щены
    0.85
     moeilijk
    0.85
    Activations Density 0.000%

    No Known Activations