© 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. 44235
    Prev
    Next
    INDEX
    Explanations

    bind

    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
    šenie
    -1.67
    uminense
    -1.65
     }))
    -1.62
    ྥ
    -1.60
     clasificación
    -1.60
     कैसी
    -1.56
    𝄆
    -1.56
    のうち
    -1.46
    ruptedException
    -1.45
     '&#
    -1.45
    POSITIVE LOGITS
    \
    1.65
     &
    1.62
     an
    1.47
    ).
    1.47
    上記
    1.40
    ではでは
    1.37
    那时
    1.36
     For
    1.36
    up
    1.35
    𐄙
    1.32
    Activations Density 0.051%

    No Known Activations