© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 60946
    Prev
    Next
    INDEX
    Explanations

    family names and titles

    np_acts-logits-general · gemini-2.5-flash-lite

    Dr. followed by names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     หาก
    0.25
    惫
    0.24
     obowią
    0.23
    方針
    0.23
    श्रे
    0.22
     ကျွန်
    0.22
     ถ้า
    0.22
    创建一个
    0.22
    ২১
    0.22
    Đây
    0.22
    POSITIVE LOGITS
     David
    0.31
     Richard
    0.30
     Michael
    0.29
     Robert
    0.29
     D
    0.28
     Joseph
    0.28
     Nicholas
    0.28
     Matthew
    0.28
     Peter
    0.26
     S
    0.26
    Activations Density 0.058%

    No Known Activations