© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 38967
    Prev
    Next
    INDEX
    Explanations

    net followed by specific words

    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
    If
    -3.66
     
    -3.64
    In
    -3.28
    ↵
    -3.16
    The
    -3.05
    They
    -3.02
    It
    -2.98
    $
    -2.91
    0
    -2.89
    We
    -2.83
    POSITIVE LOGITS
    胧
    3.17
    饪
    3.00
    詎
    2.98
     😘
    2.95
    鈇
    2.80
     😂😂😂
    2.78
    鯪
    2.72
    Ꮄ
    2.69
    ѣмъ
    2.67
    ised
    2.61
    Activations Density 0.005%

    No Known Activations