© 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. 40-GEMMASCOPE-2-RES-262K
    7. 12847
    Prev
    Next
    INDEX
    Explanations

    crypto platforms, codecademy, childhelp, copy.ai, survey junkie, ip2location

    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_40_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
    Bankr
    0.41
     بابەت
    0.40
    хождение
    0.40
     ubiquitin
    0.40
    Jefferson
    0.37
     Multipart
    0.37
    <unused2133>
    0.36
    sadpoetry
    0.36
    椑
    0.36
    ホワイト
    0.35
    POSITIVE LOGITS
    zilla
    0.52
     enthusiasts
    0.51
     lovers
    0.49
    wise
    0.48
    osaurus
    0.47
    star
    0.46
    Plus
    0.46
    나라
    0.46
    Hub
    0.46
    Mate
    0.46
    Activations Density 0.030%

    No Known Activations