© 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. 128946
    Prev
    Next
    INDEX
    Explanations

    width and height

    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
    Ahol
    -1.13
    pgs
    -1.06
     sadar
    -1.02
     frigo
    -0.98
    >;/
    -0.95
    pography
    -0.94
    bedded
    -0.94
    '|
    -0.94
     Pode
    -0.93
    ㍉
    -0.92
    POSITIVE LOGITS
    -
    1.00
    の基本
    0.95
    Tan
    0.91
    เม
    0.91
    LayoutConstraint
    0.90
     Big
    0.89
     folgt
    0.88
     rob
    0.88
    imbangan
    0.87
    ≔
    0.87
    Activations Density 0.004%

    No Known Activations