© 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. 87067
    Prev
    Next
    INDEX
    Explanations

    news, stock, ask

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

    building descriptions

    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
    Negative Logits
    kond
    0.46
     Careful
    0.44
    userId
    0.43
     করিয়ে
    0.43
    úncia
    0.43
    akala
    0.43
    tudo
    0.43
    otland
    0.42
    манда
    0.42
    ಮ
    0.41
    POSITIVE LOGITS
     অতিরিক্ত
    0.50
    <^
    0.45
    Ƅ
    0.45
    ریع
    0.43
     stockpile
    0.43
     خواهند
    0.43
    ні
    0.43
    が必要
    0.43
    ╠
    0.42
    ჯ
    0.41
    Activations Density 0.001%

    No Known Activations