© 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. 25292
    Prev
    Next
    INDEX
    Explanations

    cut any, prone skin

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

    present, followed by subject description

    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
    ঙ্গা
    0.21
    ==
    0.20
    Université
    0.19
    ęg
    0.19
     leakage
    0.19
    Delete
    0.18
    দীর
    0.18
    错误的
    0.18
    Fancy
    0.18
    Diffuse
    0.18
    POSITIVE LOGITS
    और
    0.27
    ز
    0.25
     و
    0.23
     وس
    0.23
     secund
    0.23
     ਅਤੇ
    0.23
     и
    0.23
     ഏറെ
    0.22
     és
    0.22
     عرف
    0.22
    Activations Density 0.000%

    No Known Activations