© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 8743
    Prev
    Next
    INDEX
    Explanations

    quoted or parenthetical phrases

    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
    ୍
    0.37
     प
    0.33
     প
    0.33
    pherds
    0.33
     һ
    0.32
     বেড়ে
    0.32
     মতে
    0.32
    ୍ୟ
    0.31
     क
    0.31
    0.31
    POSITIVE LOGITS
     methodology
    0.40
    اتج
    0.38
     critères
    0.37
     stej
    0.36
     glaube
    0.36
     metodologia
    0.36
    ות
    0.35
    混乱
    0.35
     कमेटी
    0.35
     tén
    0.35
    Activations Density 0.184%

    No Known Activations