© 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. 55610
    Prev
    Next
    INDEX
    Explanations

    save money or time

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

    offers significant benefits

    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
    بور
    0.50
    وت
    0.49
     brilliance
    0.47
     håll
    0.46
    y
    0.46
    ब्रा
    0.46
    te
    0.45
    ut
    0.45
    ry
    0.45
    那你
    0.45
    POSITIVE LOGITS
     transporting
    0.51
     assembling
    0.46
     కాని
    0.46
     ಭಯ
    0.45
     diminutive
    0.45
     Thieves
    0.44
     હતી
    0.44
     ಏಕೆಂದರೆ
    0.43
     ២
    0.43
     exploiting
    0.42
    Activations Density 0.000%

    No Known Activations