© 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. 84190
    Prev
    Next
    INDEX
    Explanations

    various languages and abbreviations

    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
     lipca
    -2.02
     To
    -1.98
    蚨
    -1.88
    AppRoutingModule
    -1.88
     lutego
    -1.87
    ربای
    -1.87
    gië
    -1.84
     października
    -1.84
     czerwca
    -1.80
     kwietnia
    -1.79
    POSITIVE LOGITS
    an
    2.27
    縂
    2.20
     ちゃん
    2.14
     間取り
    2.11
    ings
    2.08
    ՚
    2.06
    pecabe
    2.02
    ܆
    1.96
    out
    1.95
     実例
    1.94
    Activations Density 0.010%

    No Known Activations