© 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. 10-GEMMASCOPE-RES-131K
    7. 103542
    Prev
    Next
    INDEX
    Explanations

    a/an followed by descriptive noun

    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_10/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
     اكتوبر
    -1.62
    mathrm
    -1.49
    0
    -1.48
     muualla
    -1.48
    érience
    -1.48
     it
    -1.43
     linguri
    -1.41
     empiezan
    -1.40
     možno
    -1.39
     OSError
    -1.39
    POSITIVE LOGITS
     and
    2.17
     treu
    1.57
     logements
    1.54
     same
    1.50
     bosques
    1.43
     prins
    1.41
    Forgot
    1.41
    Same
    1.37
     carbón
    1.36
     minera
    1.35
    Activations Density 0.012%

    No Known Activations