© 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. 237957
    Prev
    Next
    INDEX
    Explanations

    contrast or continuation

    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
    Just
    0.52
    (
    0.52
    ऐ
    0.50
     Just
    0.49
     just
    0.48
    ce
    0.48
     JUST
    0.47
    c
    0.46
    茨
    0.46
    Without
    0.46
    POSITIVE LOGITS
     زندگی
    0.57
     لیکن
    0.53
     حقیقت
    0.53
     جیل
    0.52
     ಅನೇಕ
    0.52
    کار
    0.50
    زندگی
    0.49
     ساده
    0.49
     پیچ
    0.49
     ہی
    0.48
    Activations Density 0.000%

    No Known Activations