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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 123562
    Prev
    Next
    INDEX
    Explanations

    minecraft

    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
    `;
    -1.07
    }$;
    -1.07
     those
    -1.05
     aplicativos
    -1.05
     and
    -1.03
    鴎
    -1.03
     \&
    -1.02
    そちら
    -1.00
    \},
    -0.99
     after
    -0.95
    POSITIVE LOGITS
     you
    1.39
     destek
    1.25
    だそうです
    1.16
     अन्य
    1.12
     incluso
    1.09
     حتی
    1.06
    кура
    1.06
     mno
    1.03
     inoltre
    1.03
     even
    1.02
    Activations Density 0.068%

    No Known Activations