© 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. 31-GEMMASCOPE-2-RES-65K
    7. 14692
    Prev
    Next
    INDEX
    Explanations

    Caesar cipher explanations

    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_31_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
     st
    0.44
     bov
    0.42
     interests
    0.42
     thereafter
    0.42
     />
    0.41
     to
    0.41
     ()
    0.41
     obtained
    0.40
     ECM
    0.40
     presumably
    0.40
    POSITIVE LOGITS
     특히
    0.47
     चेहरा
    0.46
    ާ
    0.45
    模样
    0.45
     speziell
    0.45
    특히
    0.44
     повече
    0.43
     considérer
    0.43
     wygląda
    0.43
    喹
    0.42
    Activations Density 0.003%

    No Known Activations