© 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. 30943
    Prev
    Next
    INDEX
    Explanations

    code context or sentence endings

    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
     недостатки
    -0.79
     ObjectParameter
    -0.78
    ================
    -0.73
    AreEqual
    -0.73
     colspan
    -0.72
    teness
    -0.70
    QObject
    -0.69
    喫
    -0.69
    scienti
    -0.66
    XmlAccessType
    -0.66
    POSITIVE LOGITS
    getContext
    1.02
     getContext
    0.90
    espejo
    0.87
     forskj
    0.82
    ằm
    0.80
    anyag
    0.75
     områ
    0.73
    sediaan
    0.72
    ímos
    0.71
    خيص
    0.71
    Activations Density 0.004%

    No Known Activations