© 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. 106422
    Prev
    Next
    INDEX
    Explanations

    foreign language words

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

    steampunk

    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
    0
    0.56
    <0x80>
    0.45
    ো
    0.45
    <0x96>
    0.44
    Campbell
    0.43
    とき
    0.43
     $
    0.43
    亚
    0.42
    js
    0.42
    yaj
    0.42
    POSITIVE LOGITS
     absorbers
    0.52
     वॉलेट
    0.51
     militias
    0.49
     workbook
    0.49
     merito
    0.49
     resellers
    0.49
     proletariat
    0.48
     levers
    0.48
     humides
    0.47
    孭
    0.47
    Activations Density 0.001%

    No Known Activations