© 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. 51754
    Prev
    Next
    INDEX
    Explanations

    list item markers

    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
     ጥቅ
    0.47
     pern
    0.46
     methodological
    0.45
     х
    0.44
     그럼
    0.43
     Rü
    0.43
     종합
    0.43
    তনে
    0.42
    𒋼
    0.42
     perin
    0.42
    POSITIVE LOGITS
    ple
    0.46
    dirs
    0.45
    Vida
    0.43
    িনা
    0.42
    Being
    0.41
    ()
    0.41
    But
    0.41
    Life
    0.40
    They
    0.40
    ([],
    0.39
    Activations Density 0.013%

    No Known Activations