© 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. 192594
    Prev
    Next
    INDEX
    Explanations

    SQL queries and typescript interfaces

    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
    ($('#
    0.45
     gedung
    0.42
     above
    0.38
     ABOVE
    0.38
     ऐसी
    0.38
    Above
    0.38
     चेयरमैन
    0.37
    蓿
    0.36
    उद्योग
    0.36
    묭
    0.36
    POSITIVE LOGITS
    ंसी
    0.41
     చేసుకోవ
    0.40
    吊
    0.39
     potom
    0.38
    shots
    0.38
     गुरू
    0.38
    shooter
    0.37
    Stepper
    0.37
    unters
    0.37
     يخ
    0.37
    Activations Density 0.000%

    No Known Activations