© 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. 216957
    Prev
    Next
    INDEX
    Explanations

    naked skin or garden

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

    performance review context

    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
     барои
    0.46
     ҳ
    0.46
     듣
    0.45
     эффектив
    0.44
     pizarra
    0.44
     müs
    0.44
    이었다
    0.43
    ís
    0.43
    িক
    0.42
    ologis
    0.42
    POSITIVE LOGITS
    っきり
    0.49
    叒
    0.48
    ㄝ
    0.43
     succulent
    0.43
     tendances
    0.42
    cooler
    0.41
    桎
    0.41
    信任
    0.41
    字典
    0.40
     Sylvain
    0.40
    Activations Density 0.000%

    No Known Activations