© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 6716
    Prev
    Next
    INDEX
    Explanations

    just perfect

    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
    Negative Logits
    gezogen
    -2.05
    ensões
    -1.91
    跸
    -1.79
    wirken
    -1.78
     DIFFERENT
    -1.78
     votación
    -1.77
    CodeDom
    -1.77
    粁
    -1.77
    狨
    -1.76
    ющие
    -1.74
    POSITIVE LOGITS
    Z
    2.31
    F
    2.16
    U
    2.14
    E
    2.09
    Another
    2.08
    just
    2.05
    Just
    1.98
    Some
    1.93
     Several
    1.92
    T
    1.91
    Activations Density 0.010%

    No Known Activations