© 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. 70267
    Prev
    Next
    INDEX
    Explanations

    robotics and robotic applications

    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
    '
    -3.98
     —
    -3.09
    ↵
    -2.64
     However
    -2.64
    \
    -2.59
     ‘
    -2.52
    t
    -2.41
     was
    -2.39
    si
    -2.22
     (
    -2.22
    POSITIVE LOGITS
    糶
    3.14
    鲽
    2.83
     炖
    2.80
    archiwizowane
    2.80
    ᥫ
    2.77
    𓍊
    2.75
    
    2.72
     fotografii
    2.69
     procesu
    2.67
    ౭
    2.67
    Activations Density 0.002%

    No Known Activations