© 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. 91669
    Prev
    Next
    INDEX
    Explanations

    woman, contacted, rain coats

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

    Bakhmut

    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
    瘧
    0.50
    دیای
    0.48
    ל
    0.48
    เมื่อ
    0.48
    л
    0.47
    ल
    0.47
    ل
    0.46
    ພວກເຮ
    0.46
     disciplinas
    0.46
    陬
    0.46
    POSITIVE LOGITS
     મહિલા
    0.55
     toasted
    0.54
     toured
    0.53
     contacted
    0.52
     screwed
    0.52
     మహిళ
    0.51
     ର
    0.49
     painted
    0.49
     المرأة
    0.48
     woman
    0.47
    Activations Density 0.000%

    No Known Activations