© 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. 7443
    Prev
    Next
    INDEX
    Explanations

    stuffed things and their contents

    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
     sentra
    -2.63
    on
    -2.53
    ta
    -2.42
    鲧
    -2.38
    
    -2.23
    t
    -2.20
    B
    -2.13
     gebeten
    -2.11
    ch
    -2.06
    H
    -2.06
    POSITIVE LOGITS
     When
    2.56
    ’
    2.47
     owing
    2.42
    𐑂
    2.38
    ()]);
    2.11
    ()].
    2.09
     Using
    2.08
    ReadKey
    2.06
    身の
    2.03
    ]
    2.03
    Activations Density 0.003%

    No Known Activations