© 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. 62186
    Prev
    Next
    INDEX
    Explanations

    "and", "or", "not", "more"

    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
    のような
    0.46
    非常
    0.41
    Some
    0.40
    Other
    0.40
    ímav
    0.39
    A
    0.39
    Another
    0.39
     hanno
    0.39
     andere
    0.38
    ាតុ
    0.38
    POSITIVE LOGITS
     likewise
    0.42
    カテゴ
    0.39
     вместо
    0.38
    ථ
    0.36
    倘
    0.36
     yea
    0.35
    inelli
    0.35
    🥀
    0.35
     되
    0.35
    春夏
    0.34
    Activations Density 0.101%

    No Known Activations