© 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-65K
    7. 55527
    Prev
    Next
    INDEX
    Explanations

    nuclear detonations EMP

    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_65k_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
     )।
    0.42
    Ци
    0.41
    |।
    0.41
    鿆
    0.40
     சொல்லி
    0.40
     المسي
    0.40
    र्देश
    0.40
    স্তন
    0.40
     Él
    0.40
    蕞
    0.39
    POSITIVE LOGITS
     function
    0.46
     ex
    0.42
     shown
    0.41
     Learn
    0.40
     radius
    0.39
     dime
    0.39
     Ex
    0.38
     frequently
    0.37
    room
    0.37
     rapidly
    0.37
    Activations Density 0.003%

    No Known Activations