© 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. 22-GEMMASCOPE-RES-131K
    7. 25955
    Prev
    Next
    INDEX
    Explanations

    second round

    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_22/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
     préstamos
    -0.88
     ї
    -0.82
     doda
    -0.82
     obrazu
    -0.81
     sportifs
    -0.79
     producenta
    -0.79
     quí
    -0.78
    setOption
    -0.77
     компания
    -0.77
    iser
    -0.77
    POSITIVE LOGITS
     while
    0.84
     mientras
    0.80
    合唱
    0.78
     mentre
    0.78
     is
    0.75
     vapormax
    0.72
     DirectX
    0.71
     zatím
    0.71
    NEL
    0.71
    ngine
    0.71
    Activations Density 0.087%

    No Known Activations