© 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. 8375
    Prev
    Next
    INDEX
    Explanations

    documentation comments and annotations

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

    The neuron detects blocks of pseudo-Latin “Lorem Ipsum” filler text.

    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
    Unless
    0.68
    除非
    0.63
     Unless
    0.59
     রানের
    0.57
    ('['
    0.55
     unless
    0.53
     fileprivate
    0.52
    
    0.52
    盉
    0.52
     কেন্দ্রে
    0.52
    POSITIVE LOGITS
    運輸
    0.63
     grid
    0.57
     отме
    0.55
     осу
    0.54
    grid
    0.54
     Grid
    0.54
     placement
    0.53
     var
    0.52
     suite
    0.52
     measures
    0.52
    Activations Density 0.010%

    No Known Activations