© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 88538
    Prev
    Next
    INDEX
    Explanations

    Stradivarius and domain names

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

    after punctuation

    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
     dedicating
    0.50
    輻
    0.47
     inventing
    0.46
     transmitting
    0.46
    )$,
    0.46
    佗
    0.46
     constraining
    0.45
    حاء
    0.44
     devoting
    0.44
     spraying
    0.44
    POSITIVE LOGITS
     alimentos
    0.47
     মসজিদে
    0.45
    ue
    0.45
    ẹn
    0.43
    Depos
    0.43
    Promises
    0.42
    gaia
    0.41
    몬
    0.41
     ఉపయోగ
    0.41
    andid
    0.40
    Activations Density 0.001%

    No Known Activations