© 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. 94385
    Prev
    Next
    INDEX
    Explanations

    phrase, or pattern.Torentduewrongfrommustoffers

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

    Creative providing crucial aid

    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
     সন্ত্রাসী
    0.57
    allItems
    0.50
     ಅನುಪ
    0.49
    voucher
    0.49
    ^{*}=
    0.48
    ładow
    0.48
    ointments
    0.47
    }^{*}=\
    0.47
    frozen
    0.47
    istar
    0.46
    POSITIVE LOGITS
     në
    0.45
     Volk
    0.45
    ెం
    0.45
     cité
    0.45
     Etc
    0.45
     Temple
    0.43
     Serra
    0.43
     sakte
    0.43
     Mont
    0.43
     In
    0.42
    Activations Density 0.000%

    No Known Activations