© 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. 131210
    Prev
    Next
    INDEX
    Explanations

    course numbers and prerequisites

    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
     at
    0.45
     ११
    0.43
     Eighth
    0.42
    ۹
    0.42
     Sicher
    0.41
     ८
    0.41
    ance
    0.41
     ১১
    0.41
    ８
    0.40
     eighth
    0.40
    POSITIVE LOGITS
     मिल्
    0.40
    벙
    0.38
     кеңсесинде
    0.37
    alım
    0.36
    manın
    0.35
     hims
    0.35
     ذریع
    0.35
     deems
    0.34
    ほん
    0.34
     practition
    0.34
    Activations Density 0.001%

    No Known Activations