© 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. 123654
    Prev
    Next
    INDEX
    Explanations

    systems integration

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

    understand different

    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
    à
    0.53
     dinast
    0.52
    '))
    0.51
     ancora
    0.49
    Cheese
    0.48
     posto
    0.48
     mediante
    0.48
    1
    0.48
     الي
    0.48
    Usage
    0.48
    POSITIVE LOGITS
    нэт
    0.50
    कु
    0.50
    لت
    0.48
     Motorsports
    0.46
    راتيج
    0.45
     techs
    0.45
    कुंठ
    0.45
    reno
    0.43
    nath
    0.43
    kumar
    0.43
    Activations Density 0.000%

    No Known Activations