© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 1539
    Prev
    Next
    INDEX
    Explanations

    names, code, and phrases

    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
    ЙТЕ
    -0.84
     generated
    -0.82
     recognized
    -0.76
    čiau
    -0.75
     kept
    -0.75
     used
    -0.73
     immediately
    -0.72
     Peter
    -0.72
    TeV
    -0.72
    TA
    -0.71
    POSITIVE LOGITS
    pant
    0.92
     hissed
    0.81
     Manly
    0.80
    Glossary
    0.78
    Manu
    0.78
     Hobbs
    0.77
    zeiti
    0.77
     Niños
    0.77
     trun
    0.77
    tore
    0.75
    Activations Density 0.004%

    No Known Activations