© 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
    5. 40-GEMMASCOPE-2-RES-16K
    7. 9338
    Prev
    Next
    INDEX
    Explanations

    shaking or shaking off

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

    shaking and vibrating

    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
    Not in Any Lists

    No Comments

    Negative Logits
    glRaster
    0.42
     έκ
    0.41
    chap
    0.41
     అయిన
    0.39
    潮
    0.38
    kJ
    0.38
     بک
    0.37
    chad
    0.37
    odora
    0.37
    quadratic
    0.36
    POSITIVE LOGITS
     shake
    2.28
     shakes
    2.17
     shaking
    2.13
    Shake
    2.06
     Shake
    2.05
     shook
    1.98
    shake
    1.95
     shaken
    1.86
    shakes
    1.77
    搖
    1.66
    Activations Density 0.144%

    No Known Activations