© 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. 34-GEMMASCOPE-RES-131K
    7. 47697
    Prev
    Next
    INDEX
    Explanations

    protected under law

    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_34/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
    ężczy
    -0.77
    сах
    -0.75
    ceğini
    -0.74
     Shannon
    -0.73
    hamma
    -0.72
    ליון
    -0.70
     byť
    -0.68
     tárgy
    -0.68
     NDEBUG
    -0.66
    Už
    -0.66
    POSITIVE LOGITS
     protected
    6.31
    protected
    5.66
     Protected
    4.97
    Protected
    4.75
    PROTECT
    3.56
     PROTECT
    3.55
     unprotected
    3.34
     protect
    3.16
     защи
    2.97
     protegido
    2.97
    Activations Density 0.056%

    No Known Activations