© 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-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 24034
    Prev
    Next
    INDEX
    Explanations

    version numbers and formats

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ورژن
    0.54
     version
    0.51
    ג
    0.50
    g
    0.50
    的版本
    0.49
     versione
    0.48
     версия
    0.47
    c
    0.46
     версии
    0.45
    Version
    0.44
    POSITIVE LOGITS
    ట్స్‌మన్
    0.40
     JsonResult
    0.40
    criptions
    0.39
     Scripture
    0.39
    cription
    0.38
    ังสือ
    0.38
    emption
    0.38
    gação
    0.36
     repentance
    0.36
    MainBinding
    0.36
    Activations Density 0.002%

    No Known Activations