© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 44583
    Prev
    Next
    INDEX
    Explanations

    code structure delimiters

    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
    튿
    -2.25
     วิ
    -2.13
    쨩
    -2.00
    蟥
    -1.97
    atique
    -1.93
    llll
    -1.91
     โ
    -1.91
    wouldn
    -1.91
    oused
    -1.90
    uride
    -1.90
    POSITIVE LOGITS
     and
    2.80
     not
    2.66
     of
    2.64
     does
    2.48
     this
    2.47
     for
    2.44
     from
    2.41
     what
    2.31
     with
    2.27
     while
    2.25
    Activations Density 0.039%

    No Known Activations