© 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. 166518
    Prev
    Next
    INDEX
    Explanations

    dialogue, demand, staying, suggests, September, interior, sucking

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

    CISSP exam study

    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
    оборот
    0.48
     hjälp
    0.48
     അന്വേഷ
    0.48
    ="))
    0.47
     इंपोर्ट
    0.46
    }^{*}=\
    0.46
    ंत्रिक
    0.46
    umlahan
    0.46
     bantuan
    0.45
    }=\{\
    0.45
    POSITIVE LOGITS
    是
    0.50
    ي
    0.50
     Radius
    0.48
    দানি
    0.48
     Walgreens
    0.46
     Inspire
    0.44
    s
    0.44
     Traffic
    0.43
     apartments
    0.43
     terminals
    0.43
    Activations Density 0.000%

    No Known Activations