© 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-IT
    5. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 79821
    Prev
    Next
    INDEX
    Explanations

    Russian words starting with "Про"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_0_width_262k_l0_small_affine
    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
    ਰ
    1.78
    !
    1.48
    ER
    1.34
    в
    1.34
    س
    1.34
    н
    1.30
    r
    1.26
    ਮ
    1.26
    не
    1.25
    ран
    1.25
    POSITIVE LOGITS
     informazioni
    1.30
    人
    1.30
    _
    1.28
    ために
    1.26
    al
    1.23
    ല്ലാം
    1.23
    も
    1.22
    人不
    1.21
    ле
    1.20
    तः
    1.17
    Activations Density 0.000%

    No Known Activations