© 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. 103957
    Prev
    Next
    INDEX
    Explanations

    comfort compared with

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

    difference and understanding

    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
    ారు
    0.46
    ህ
    0.45
    binomial
    0.43
    rawn
    0.43
    sight
    0.43
    攔
    0.42
     raven
    0.42
    遐
    0.42
    റെ
    0.42
    人在
    0.41
    POSITIVE LOGITS
     Ники
    0.49
     تھا۔
    0.47
     wszystkie
    0.47
     كلها
    0.47
     المؤ
    0.45
     Einsch
    0.45
     முடிக்க
    0.45
     层
    0.45
     Stimme
    0.44
     وضعیت
    0.44
    Activations Density 0.000%

    No Known Activations