© 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. 30194
    Prev
    Next
    INDEX
    Explanations

    languages other than english

    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
    :
    0.35
     shenanigans
    0.34
     এবং
    0.33
     và
    0.32
     smuggling
    0.32
    ",
    0.31
     &
    0.31
    ”,
    0.31
    \
    0.31
     contexts
    0.31
    POSITIVE LOGITS
    डेन
    0.30
    ట్స్‌మన్
    0.29
    ivät
    0.28
    개월
    0.28
     मरम्मत
    0.28
    عهد
    0.27
     නමුත්
    0.27
     உலோக
    0.27
     தூசி
    0.26
    व्हाण
    0.26
    Activations Density 0.000%

    No Known Activations