© 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. 7738
    Prev
    Next
    INDEX
    Explanations

    install, activate, or usage

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

    The neuron is detecting unusually rare or uncommon words and tokens.

    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
    annte
    0.79
    र
    0.75
     другого
    0.74
    ্সে
    0.73
     जिन्हें
    0.72
     цветы
    0.72
     इसीलिए
    0.71
    ).\\
    0.71
     желательно
    0.71
     #[
    0.70
    POSITIVE LOGITS
    su
    0.82
     Lalu
    0.78
    رق
    0.76
    bru
    0.74
    Bước
    0.74
    thrust
    0.74
    sv
    0.73
    sé
    0.70
    kontrol
    0.70
    sac
    0.69
    Activations Density 0.000%

    No Known Activations