© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 53-GEMMASCOPE-2-RES-262K
    7. 50250
    Prev
    Next
    INDEX
    Explanations

    adverbs and adjectives

    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
    ąg
    0.38
    తిక
    0.38
     mahdoll
    0.36
     gick
    0.35
    yelination
    0.34
     "=",
    0.34
    penny
    0.33
    漃
    0.33
    퓰
    0.33
    elementAt
    0.33
    POSITIVE LOGITS
    istically
    1.54
    하게
    1.52
    ingly
    1.51
    iously
    1.48
    的に
    1.48
    hetically
    1.43
    ably
    1.41
    ously
    1.41
     있게
    1.41
    ively
    1.39
    Activations Density 0.044%

    No Known Activations