© 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-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 19856
    Prev
    Next
    INDEX
    Explanations

    something to do

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_65k_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
     گئی
    0.44
    Alchemy
    0.43
    二氧化
    0.43
    Formerly
    0.43
    Aldrich
    0.42
    NER
    0.42
    єю
    0.42
    Ằ
    0.42
    分别是
    0.42
    NAMES
    0.41
    POSITIVE LOGITS
     that
    0.64
     você
    0.63
    that
    0.61
     که
    0.59
     we
    0.58
     pueden
    0.57
     dapat
    0.56
     που
    0.54
     you
    0.54
     могат
    0.54
    Activations Density 0.037%

    No Known Activations