© 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. 10764
    Prev
    Next
    INDEX
    Explanations

    non-english text or special characters

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

    The neuron flags unusually capitalized or out-of-place uppercase words in the middle of running 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_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
    s
    1.10
    
    0.95
    ים
    0.93
    }$;
    0.91
    }$,
    0.83
     이곳
    0.82
    tob
    0.80
    니
    0.80
    ב
    0.80
    며
    0.79
    POSITIVE LOGITS
    ကျော်
    0.83
    နည်း
    0.75
     Dör
    0.75
    般
    0.75
    хождение
    0.74
    ेक्ट
    0.71
     Màu
    0.70
    achel
    0.69
    とっても
    0.68
    خوا
    0.68
    Activations Density 0.000%

    No Known Activations