© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 213382
    Prev
    Next
    INDEX
    Explanations

    board approved actions

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

    specific terms, jargon, and technical concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     experiential
    0.45
     Despite
    0.42
     رغم
    0.38
     spontaneity
    0.38
     vibrancy
    0.38
     haystack
    0.38
     omnichannel
    0.38
     despite
    0.37
    Despite
    0.37
     &-
    0.37
    POSITIVE LOGITS
     ガ
    0.49
     modificare
    0.48
    ak
    0.46
    改装
    0.46
    modif
    0.45
     நடவடிக்கை
    0.44
    鉱
    0.44
    Ко
    0.44
    Especific
    0.43
    ガ
    0.43
    Activations Density 0.002%

    No Known Activations