© 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-IT
    5. 24-GEMMASCOPE-2-RES-262K
    7. 9641
    Prev
    Next
    INDEX
    Explanations

    neurological, architect, achievable, careful, name, strengths

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_24_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Synonym
    0.71
     Lantern
    0.71
     և
    0.70
    。「
    0.70
     Sequences
    0.69
    。"
    0.67
     পর্যবেক্ষণ
    0.67
    द्वारे
    0.66
    。\
    0.66
    。[
    0.66
    POSITIVE LOGITS
    on
    0.94
    न
    0.87
    a
    0.86
    ن
    0.85
    n
    0.84
    ol
    0.83
    ون
    0.83
    x
    0.82
    nade
    0.78
    id
    0.77
    Activations Density 0.001%

    No Known Activations