© 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-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 2182
    Prev
    Next
    INDEX
    Explanations

    Returns:

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     mish
    0.43
     oscillating
    0.42
     scorched
    0.41
     %(
    0.40
     soup
    0.39
     mischief
    0.38
     extravagant
    0.38
    透过
    0.38
     subm
    0.37
     tot
    0.36
    POSITIVE LOGITS
     RETURNS
    0.42
     Yine
    0.42
    $&$-
    0.41
    raising
    0.40
    //@
    0.40
    CHINA
    0.40
    횟
    0.40
    #-
    0.39
    earic
    0.39
    中国的
    0.39
    Activations Density 0.001%

    No Known Activations