© 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. 22-GEMMASCOPE-RES-131K
    7. 26736
    Prev
    Next
    INDEX
    Explanations

    the word statement

    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_22/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
     -
    -2.77
     They
    -2.77
     The
    -2.73
     :"
    -2.45
     在
    -2.39
     aloof
    -2.33
     "-
    -2.30
     "
    -2.30
     Your
    -2.22
     这
    -2.14
    POSITIVE LOGITS
    酲
    3.13
    涠
    2.97
    岨
    2.81
    
    2.72
    肏
    2.69
    啬
    2.52
    !”
    2.50
    ”:
    2.47
    ꯵
    2.47
    “
    2.45
    Activations Density 0.012%

    No Known Activations