© 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. 31-GEMMASCOPE-2-RES-262K
    7. 194015
    Prev
    Next
    INDEX
    Explanations

    gusty wind

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

    Expect significant

    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_31_width_262k_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
     КП
    0.49
     않았다
    0.47
     감독
    0.46
     다니
    0.46
     필수
    0.46
     나오는
    0.45
    ikap
    0.45
    廾
    0.45
     систе
    0.44
     substituents
    0.44
    POSITIVE LOGITS
    an
    0.51
    press
    0.50
    ser
    0.49
    st
    0.48
    at
    0.46
    the
    0.46
    cess
    0.45
    主題
    0.45
     wardrobe
    0.44
    v
    0.44
    Activations Density 0.000%

    No Known Activations