© 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. 136742
    Prev
    Next
    INDEX
    Explanations

    western women storytelling

    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
    eris
    0.44
    velope
    0.42
    秸
    0.41
     Graham
    0.41
    ulz
    0.40
     вариан
    0.39
     scum
    0.39
     transcript
    0.38
     ट्रेनिंग
    0.38
    screenshots
    0.38
    POSITIVE LOGITS
    StatusBar
    0.38
     StatusBar
    0.38
     statusBar
    0.38
     È
    0.37
    хих
    0.37
     スマ
    0.36
     র‌্যা
    0.36
    スマ
    0.36
    рованных
    0.36
    ◑
    0.35
    Activations Density 0.004%

    No Known Activations