© 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. 178528
    Prev
    Next
    INDEX
    Explanations

    Graphic, education, business, Suzuki

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

    journey itself, slightly delayed

    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
    zones
    0.41
    łki
    0.40
    를
    0.39
     considerably
    0.39
    FERRED
    0.38
    elae
    0.38
    ferred
    0.38
     السابق
    0.38
    utable
    0.38
    ρες
    0.37
    POSITIVE LOGITS
     ومرحبا
    0.45
     contribuer
    0.45
     وخت
    0.44
    屎
    0.44
     vstup
    0.44
     peep
    0.43
     bén
    0.43
     لوبو
    0.42
     квіт
    0.42
     njemu
    0.42
    Activations Density 0.001%

    No Known Activations