© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 7632
    Prev
    Next
    INDEX
    Explanations

    irregularities, inconsistencies, inefficiencies, inequalities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ль
    -2.08
    Ⅳ
    -1.87
     Affaires
    -1.86
    ###########
    -1.78
     ¨
    -1.74
     Ause
    -1.72
    ));
    -1.70
    то
    -1.66
     dagli
    -1.66
     We
    -1.64
    POSITIVE LOGITS
     that
    2.31
     zakoń
    2.16
     in
    2.09
    7
    1.90
    いかがでしたか
    1.76
    なども
    1.72
    専用の
    1.66
     logistical
    1.66
    8
    1.65
    6
    1.64
    Activations Density 0.080%

    No Known Activations