© 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. 233039
    Prev
    Next
    INDEX
    Explanations

    copyright notices

    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
    ння
    0.50
    멍
    0.49
    نين
    0.48
    럏
    0.48
    طلاق
    0.47
    дени
    0.47
     Иң
    0.47
    明顯
    0.47
    鄧
    0.47
    નિક
    0.47
    POSITIVE LOGITS
    is
    0.54
    my
    0.46
    vit
    0.46
    ol
    0.45
     Dept
    0.45
    ar
    0.44
     Up
    0.44
     Carb
    0.44
    l
    0.43
    materials
    0.43
    Activations Density 0.000%

    No Known Activations