© 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. 40-GEMMASCOPE-2-RES-262K
    7. 220451
    Prev
    Next
    INDEX
    Explanations

    Russia, sound, print, elevation, gloves

    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_40_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
     интеллек
    0.43
    MESSAGE
    0.42
     Bloody
    0.40
    人工
    0.39
    🫣
    0.39
    二
    0.38
     Springfield
    0.38
     অহ
    0.38
     яку
    0.37
     Göteborg
    0.37
    POSITIVE LOGITS
     obtainable
    0.43
    韭
    0.38
     siquiera
    0.38
     किससे
    0.37
     comboBox
    0.36
     filos
    0.36
    涷
    0.36
     attainable
    0.35
     kilom
    0.35
    matica
    0.35
    Activations Density 0.003%

    No Known Activations