© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 55042
    Prev
    Next
    INDEX
    Explanations

    Russian or Slavic words

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

    request for leave

    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
    Not in Any Lists

    No Comments

    Negative Logits
     unsupervised
    0.42
    장의
    0.41
     eventual
    0.40
     proprie
    0.40
    untary
    0.40
    ુપ
    0.40
    箪
    0.40
     dabb
    0.39
    기는
    0.39
     prides
    0.39
    POSITIVE LOGITS
    aseti
    0.47
    .*/
    0.46
     вроде
    0.45
    дай
    0.44
     Чтобы
    0.44
     YA
    0.43
     Германия
    0.43
    .");
    0.43
    chik
    0.41
    akad
    0.41
    Activations Density 0.000%

    No Known Activations