© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 101262
    Prev
    Next
    INDEX
    Explanations

    vessels and appliances

    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
    
    -1.69
     étrangers
    -1.57
     ERSITY
    -1.52
    5
    -1.52
     alemão
    -1.49
    
    -1.47
     WINNER
    -1.46
    鹩
    -1.43
     qualités
    -1.42
    Élet
    -1.42
    POSITIVE LOGITS
     of
    2.38
     two
    1.94
     our
    1.71
     BEFORE
    1.63
     We
    1.49
    でしょ
    1.44
     hemos
    1.38
     When
    1.37
     Schloß
    1.36
    後の
    1.34
    Activations Density 0.014%

    No Known Activations