© 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. 68577
    Prev
    Next
    INDEX
    Explanations

    property

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

    diary, fee, rate

    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
     هذ
    0.54
     حذف
    0.53
     شكل
    0.50
     كون
    0.48
     دش
    0.47
    便于
    0.47
     ర
    0.45
     অবলম্বন
    0.45
     கொல்ல
    0.44
    啬
    0.44
    POSITIVE LOGITS
    uring
    0.50
    rate
    0.47
     Cheetah
    0.46
     Diary
    0.46
    diary
    0.45
    lines
    0.44
    presas
    0.44
    linhas
    0.44
     dicas
    0.44
    ective
    0.44
    Activations Density 0.001%

    No Known Activations