© 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. 26501
    Prev
    Next
    INDEX
    Explanations

    glaucoma and glenn names

    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
    瀦
    -3.25
     That
    -3.13
    elernt
    -3.08
    rowable
    -3.03
    塤
    -2.91
    豋
    -2.83
    瞜
    -2.80
    猻
    -2.77
    餿
    -2.67
    盦
    -2.66
    POSITIVE LOGITS
    ]
    3.81
    ’
    3.70
    "
    3.22
    2
    3.16
     '
    3.05
    ;
    2.97
    [
    2.95
    0
    2.94
    8
    2.73
    1
    2.69
    Activations Density 0.025%

    No Known Activations