© 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. 53-GEMMASCOPE-2-RES-262K
    7. 62832
    Prev
    Next
    INDEX
    Explanations

    proverb, adage, saying, idiom

    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_53_width_262k_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
    屶
    0.45
     &=\
    0.42
     fieldContext
    0.41
     khung
    0.39
     onDestroy
    0.39
    埛
    0.38
    ዖ
    0.38
     اسئله
    0.37
     ներ
    0.37
     output
    0.37
    POSITIVE LOGITS
     proverb
    2.27
     adage
    1.99
     saying
    1.70
     motto
    1.63
    諺
    1.59
     proverbial
    1.59
     Proverbs
    1.59
     sayings
    1.56
    谚
    1.53
     axiom
    1.52
    Activations Density 0.034%

    No Known Activations