© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 137426
    Prev
    Next
    INDEX
    Explanations

    Core concepts

    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
    বৈ
    0.41
     موس
    0.40
     terme
    0.39
    觛
    0.39
     نهر
    0.38
    稦
    0.38
    経
    0.38
    ռ
    0.38
    記錄
    0.38
    കൾ
    0.38
    POSITIVE LOGITS
    ungkinan
    0.42
     мотива
    0.42
     ٹرسٹ
    0.42
    abá
    0.42
     પડ
    0.41
    ídia
    0.41
    𝕞
    0.39
     haies
    0.38
    Artista
    0.38
     पुजारी
    0.38
    Activations Density 0.002%

    No Known Activations