© 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. 21495
    Prev
    Next
    INDEX
    Explanations

    swapping or exchanging

    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
     \
    -3.64
    ⸫
    -2.67
    簠
    -2.61
    錵
    -2.47
    聼
    -2.42
     The
    -2.41
    
    -2.39
    衚
    -2.38
    薆
    -2.36
    轳
    -2.34
    POSITIVE LOGITS
    a
    2.92
    d
    2.59
    ínsula
    2.53
    e
    2.34
    ".
    2.30
    ....
    2.25
    :
    2.23
     beset
    2.20
    Like
    2.14
    .......
    2.14
    Activations Density 0.003%

    No Known Activations