© 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. 31-GEMMASCOPE-2-RES-65K
    7. 46448
    Prev
    Next
    INDEX
    Explanations

    foreign language phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_65k_l0_medium
    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
     ook
    0.34
     bagus
    0.30
    <unused309>
    0.29
    aled
    0.27
     theyre
    0.27
    ριο
    0.27
    ্ল
    0.26
    rared
    0.26
    ogan
    0.26
    <unused328>
    0.26
    POSITIVE LOGITS
     laissez
    0.31
     veracity
    0.29
     complementarity
    0.28
     زمانے
    0.28
    最後に
    0.27
    ङ
    0.27
    نے
    0.27
     modus
    0.26
     finales
    0.26
     وړاندوینې
    0.26
    Activations Density 0.003%

    No Known Activations