© 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-262K
    7. 4414
    Prev
    Next
    INDEX
    Explanations

    HOPE hotline

    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_262k_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
    ك
    0.32
    btnUn
    0.31
     avec
    0.30
    ongono
    0.30
     juge
    0.30
    ustos
    0.30
     imprend
    0.29
    ürn
    0.29
     كنا
    0.29
    idalgo
    0.29
    POSITIVE LOGITS
    а
    0.37
    А
    0.31
    о
    0.29
    5
    0.28
    预览
    0.27
    Р
    0.27
    8
    0.27
    ’
    0.26
    З
    0.26
     Horizontal
    0.26
    Activations Density 0.054%

    No Known Activations