© 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. 34226
    Prev
    Next
    INDEX
    Explanations

    following a tutorial

    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
     The
    -3.81
    -
    -3.09
     ก็
    -3.09
    ).
    -3.08
     If
    -3.06
     But
    -3.00
    ",
    -2.89
     You
    -2.78
     -
    -2.77
    ,"
    -2.67
    POSITIVE LOGITS
    酲
    3.34
     撮っ
    3.33
    𐐀
    3.31
    ization
    3.19
    逦
    3.09
    ulation
    2.91
    ции
    2.89
    
    2.81
     ſie
    2.75
    下一篇
    2.73
    Activations Density 0.020%

    No Known Activations