© 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. 21416
    Prev
    Next
    INDEX
    Explanations

    Marshal, fromJson, AL

    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
     большая
    -3.50
    麈
    -3.27
     высокая
    -3.27
    搥
    -3.08
    柺
    -3.06
     ženy
    -3.00
    醅
    -2.95
    
    -2.95
    驺
    -2.92
     andere
    -2.88
    POSITIVE LOGITS
    1
    4.78
    er
    3.50
    6
    3.17
    7
    3.16
    8
    3.11
    4
    3.03
    -
    2.97
    to
    2.83
    In
    2.78
    5
    2.75
    Activations Density 0.001%

    No Known Activations