© 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. 86290
    Prev
    Next
    INDEX
    Explanations

    Development of

    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
     to
    -2.06
    尨
    -2.05
     is
    -1.88
    现在的
    -1.76
     senere
    -1.70
     seleccionamos
    -1.70
    ⤥
    -1.68
    для
    -1.68
    咆
    -1.65
     proposées
    -1.64
    POSITIVE LOGITS
    y
    2.44
    ar
    1.98
    </h3>
    1.95
    '
    1.92
    s
    1.91
    鬭
    1.86
    ":
    1.85
    蔸
    1.83
    ’
    1.80
    "",
    1.77
    Activations Density 0.000%

    No Known Activations