© 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. 86040
    Prev
    Next
    INDEX
    Explanations

    transcending limits or boundaries

    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
    ?"
    -2.94
    栳
    -2.81
    鴬
    -2.80
    歘
    -2.66
     使っ
    -2.59
     The
    -2.53
    ließen
    -2.52
    푆
    -2.52
    齜
    -2.52
    臜
    -2.50
    POSITIVE LOGITS
    $
    3.28
    تیجه
    3.13
    It
    3.11
    他
    2.98
    нутрен
    2.94
     Some
    2.83
    地區
    2.81
     neue
    2.64
    s
    2.64
    The
    2.61
    Activations Density 0.012%

    No Known Activations