© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26
    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B
    3. 40-GEMMASCOPE-2-RES-16K
    4. 8169
    Prev
    Next
    INDEX
    Explanations

    towel features

    np_acts-logits-general · gemini-2.5-flash-lite

    pointing down

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_40_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     ies
    0.46
    姒
    0.36
    ?,
    0.36
    jsko
    0.36
    <0xC2>
    0.36
    מק
    0.34
    /
    0.34
     tion
    0.33
    никах
    0.33
    рь
    0.32
    POSITIVE LOGITS
    <start_of_image>
    1.71
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    1.38
    ↵↵↵↵↵↵↵↵↵↵↵↵↵
    1.36
    ↵↵↵↵↵↵↵↵↵
    1.32
    ↵↵↵↵↵↵↵↵↵↵↵
    1.31
    ↵↵↵↵↵↵↵
    1.30
    ↵↵↵↵↵↵↵↵↵↵↵↵
    1.29
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    1.29
    ↵↵↵↵↵↵↵↵↵↵
    1.27
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    1.27
    Activations Density 0.334%

    No Known Activations