© 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-262K
    7. 8230
    Prev
    Next
    INDEX
    Explanations

    foreign language words

    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_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
     uses
    0.35
     Additionally
    0.34
     include
    0.33
     indicates
    0.33
     (
    0.32
     example
    0.31
    B
    0.31
     refers
    0.31
     aims
    0.31
    }
    0.31
    POSITIVE LOGITS
    仿佛
    0.40
     ένα
    0.35
     सच्चे
    0.35
    một
    0.34
     इतनी
    0.33
     sebuah
    0.32
    まるで
    0.32
     그죠
    0.32
     마치
    0.32
     όχι
    0.31
    Activations Density 0.394%

    No Known Activations