© 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. 99326
    Prev
    Next
    INDEX
    Explanations

    authorship and roles

    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
     to
    -2.52
    2
    -1.79
     two
    -1.75
     but
    -1.73
    ti
    -1.73
    “
    -1.73
    ."
    -1.73
    ):
    -1.66
    or
    -1.60
     =
    -1.59
    POSITIVE LOGITS
    
    1.85
     jesús
    1.64
     pernic
    1.63
     refugi
    1.59
    鶫
    1.58
    ኬ
    1.56
    罍
    1.52
    Guerra
    1.52
     kimdir
    1.51
     fernández
    1.50
    Activations Density 0.002%

    No Known Activations