© 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. 1563
    Prev
    Next
    INDEX
    Explanations

    unidiff format

    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
    isos
    0.47
    വണ
    0.44
    lements
    0.43
    隰
    0.41
    ফস
    0.40
    ᐳ
    0.40
    ಿದ್ದಾನೆ
    0.39
     circunferência
    0.39
    WaitingTime
    0.38
    imientos
    0.38
    POSITIVE LOGITS
     Top
    0.40
    @@
    0.38
     Senior
    0.37
     Asia
    0.37
     Line
    0.37
     Yard
    0.36
    0.35
     asia
    0.35
     b
    0.34
     Soon
    0.34
    Activations Density 0.000%

    No Known Activations