© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 113047
    Prev
    Next
    INDEX
    Explanations

    russian words ending in ский or лла

    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_2_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
    이랑
    0.44
    在
    0.44
    𝙞
    0.41
    不允许
    0.40
    Z
    0.40
     провер
    0.38
     ktorí
    0.38
    Q
    0.37
    W
    0.37
     berücksicht
    0.36
    POSITIVE LOGITS
    ку
    0.60
    ма
    0.59
    it
    0.51
    ين
    0.49
    き
    0.46
    t
    0.46
    یس
    0.46
    ні
    0.44
    ८
    0.44
    1
    0.43
    Activations Density 0.000%

    No Known Activations