© 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. 53-GEMMASCOPE-2-RES-262K
    7. 85642
    Prev
    Next
    INDEX
    Explanations

    US state capitals

    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_53_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
    kraft
    0.37
     Nh
    0.36
    श्न
    0.35
    Bet
    0.35
    bet
    0.35
    hbar
    0.35
    Motion
    0.35
    伯
    0.35
     kraft
    0.34
     Kxf
    0.34
    POSITIVE LOGITS
     Concord
    0.44
     extrémité
    0.39
     alleys
    0.39
     şekilde
    0.39
     BCA
    0.39
     alley
    0.38
     Capitol
    0.38
     బ్యాంకు
    0.38
     Chun
    0.38
     McA
    0.38
    Activations Density 0.003%

    No Known Activations