© 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. 181819
    Prev
    Next
    INDEX
    Explanations

    man of unclean lips

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

    management skills, reform movements

    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
    艙
    0.54
    Buck
    0.52
    ف
    0.48
    ام
    0.48
     Buckley
    0.46
    粗
    0.46
    St
    0.46
    Skill
    0.46
    window
    0.45
    King
    0.44
    POSITIVE LOGITS
    вии
    0.48
     چنین
    0.48
    ogenies
    0.46
    ӓ
    0.45
    رمی
    0.45
     sebagian
    0.45
    нии
    0.44
    ribusi
    0.44
     다니
    0.44
    emias
    0.43
    Activations Density 0.000%

    No Known Activations