© 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. 46196
    Prev
    Next
    INDEX
    Explanations

    reasoning and review

    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
     admixture
    0.42
    কমার
    0.39
     esche
    0.38
     unprofitable
    0.38
    色々
    0.38
     schm
    0.38
    }]$.
    0.38
     microbe
    0.38
    ნ
    0.37
     arcane
    0.37
    POSITIVE LOGITS
     YMCA
    0.48
     καθώς
    0.47
     從
    0.45
     является
    0.44
     MDF
    0.44
     دليل
    0.43
     स्पष्ट
    0.43
     étoiles
    0.43
     从
    0.42
     Национальный
    0.42
    Activations Density 0.016%

    No Known Activations