© 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. 16-GEMMASCOPE-2-RES-65K
    7. 3362
    Prev
    Next
    INDEX
    Explanations

    sound effects and design

    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_16_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
     in
    1.72
    在
    1.39
    1.37
    もら
    1.28
     In
    1.16
     في
    1.02
    も
    1.02
    ও
    1.01
     It
    1.00
     в
    1.00
    POSITIVE LOGITS
    (
    1.37
     be
    1.27
    {
    1.24
    3
    1.19
    い
    1.16
    ת
    1.15
    고
    1.11
    Sound
    1.10
    2
    1.09
    ها
    1.08
    Activations Density 0.146%

    No Known Activations