© 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. 9097
    Prev
    Next
    INDEX
    Explanations

    is Key and All

    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
    χει
    0.44
    عد
    0.39
     প্রতিনি
    0.39
    െയി
    0.38
    ,/
    0.37
    या
    0.36
    χε
    0.36
    伍
    0.36
    在
    0.36
    ुरा
    0.36
    POSITIVE LOGITS
     a
    0.60
     awesome
    0.44
    RAEL
    0.44
    케
    0.44
     an
    0.44
     official
    0.43
     your
    0.43
    verkehr
    0.42
     headquartered
    0.42
     explicabo
    0.42
    Activations Density 0.079%

    No Known Activations