© 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. 67550
    Prev
    Next
    INDEX
    Explanations

    reporting information

    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
    。
    -2.17
    '
    -2.09
    、
    -2.08
    _{
    -2.06
    }\
    -2.02
    }{
    -2.00
    ↵↵
    -1.98
    のように
    -1.97
    ).
    -1.96
     '
    -1.93
    POSITIVE LOGITS
    豋
    2.31
    佧
    2.09
    ︕
    2.06
    自己是
    1.99
    取决
    1.98
    味は
    1.94
    ܃
    1.92
    ↓↓
    1.88
     ſch
    1.88
    そうですが
    1.86
    Activations Density 0.038%

    No Known Activations