© 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. 102586
    Prev
    Next
    INDEX
    Explanations

    some of the

    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
     I
    -1.89
    use
    -1.70
    as
    -1.69
    for
    -1.68
     Überprüfung
    -1.66
     there
    -1.63
     появляется
    -1.63
    是最
    -1.63
     "
    -1.61
    ---
    -1.59
    POSITIVE LOGITS
     اگر
    2.06
    嫱
    1.99
    chnung
    1.98
    衎
    1.96
    riezmann
    1.95
    ,“
    1.93
    っている
    1.88
    ﭽ
    1.88
    衚
    1.88
    觧
    1.85
    Activations Density 0.026%

    No Known Activations