© 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. 167739
    Prev
    Next
    INDEX
    Explanations

    final outcome or subsequent events

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

    thereafter

    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
     técnicos
    0.54
    alamu
    0.51
    윅
    0.48
    льку
    0.47
     વપરા
    0.47
    ב
    0.47
     servidores
    0.47
     encontramos
    0.46
     अस्पतालों
    0.46
    ૉ
    0.46
    POSITIVE LOGITS
    之后的
    0.50
     for
    0.50
    以后
    0.48
     abutting
    0.44
     thereafter
    0.44
     permitting
    0.43
     পরবর্তীতে
    0.42
    近期
    0.42
    后的
    0.42
     Thereafter
    0.42
    Activations Density 0.001%

    No Known Activations