© 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. 128474
    Prev
    Next
    INDEX
    Explanations

    various languages

    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
    。「
    -1.64
    rées
    -1.55
    ;
    -1.49
    ();
    -1.48
    。“
    -1.46
     their
    -1.45
    ску
    -1.44
    ftes
    -1.43
    ();
    -1.43
    );
    -1.42
    POSITIVE LOGITS
     besonder
    1.73
     savait
    1.41
     rilass
    1.39
    來了
    1.38
     cóc
    1.37
     velkommen
    1.36
     получают
    1.36
     kağıt
    1.35
    差不多
    1.34
     dát
    1.30
    Activations Density 0.000%

    No Known Activations