© 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. 99169
    Prev
    Next
    INDEX
    Explanations

    part of a collection

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

    women wearing shoes without socks

    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
     Kickstarter
    0.52
    还不
    0.48
    随着
    0.46
    聽
    0.46
     ഉ
    0.45
    TikTok
    0.45
    听
    0.45
    劳
    0.45
    Middleware
    0.44
     Sanjay
    0.44
    POSITIVE LOGITS
     else
    0.48
     lymphoid
    0.46
     catchment
    0.45
     constellations
    0.45
     phyl
    0.45
     contractions
    0.45
     lymph
    0.45
     seepage
    0.44
     combinations
    0.44
     eles
    0.44
    Activations Density 0.002%

    No Known Activations