© 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-16K
    7. 5066
    Prev
    Next
    INDEX
    Explanations

    money, tower, lunar, am

    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_16k_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
    6
    0.33
    쾺
    0.33
    ྵ
    0.32
    ร้อม
    0.32
    Rue
    0.32
     США
    0.31
    ясплат
    0.31
    vertrag
    0.31
    铝
    0.31
     थाना
    0.30
    POSITIVE LOGITS
     mischievous
    0.39
     acrobat
    0.34
     Introduction
    0.33
     Eurovision
    0.33
     for
    0.32
     on
    0.32
     beginning
    0.32
     Greenpeace
    0.32
     Story
    0.31
     Transformation
    0.31
    Activations Density 0.000%

    No Known Activations