© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 75515
    Prev
    Next
    INDEX
    Explanations

    as expected

    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
    fgaben
    -0.91
     PARTE
    -0.90
     Dica
    -0.88
    Élet
    -0.88
     Prova
    -0.87
    єте
    -0.85
    σθαι
    -0.85
    ᄉ
    -0.84
    AYE
    -0.84
     Piscina
    -0.83
    POSITIVE LOGITS
     expected
    8.44
    expected
    6.66
    Expected
    6.06
     Expected
    5.94
     anticipated
    4.97
    EXPECTED
    4.72
     esperado
    4.16
     expect
    4.13
     EXPECT
    4.13
     ожида
    3.94
    Activations Density 0.199%

    No Known Activations