© 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. 5189
    Prev
    Next
    INDEX
    Explanations

    before walls, for processing

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

    This neuron detects occurrences of the word “warranty,” especially in legal disclaimer contexts.

    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
     contrô
    0.87
     Lâm
    0.82
    看见
    0.77
     colonel
    0.76
    鰤
    0.76
     thành
    0.75
     două
    0.75
    chyné
    0.73
     scă
    0.72
    प्टेंबर
    0.72
    POSITIVE LOGITS
    reminder
    0.80
    ars
    0.79
    t
    0.79
    iones
    0.75
    Enc
    0.74
    ITO
    0.73
    ención
    0.73
    ener
    0.72
     느낌
    0.72
    olicy
    0.71
    Activations Density 0.000%

    No Known Activations