© 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. 22-GEMMASCOPE-RES-131K
    7. 13916
    Prev
    Next
    INDEX
    Explanations

    get;

    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_22/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
     because
    -2.14
     which
    -1.94
     that
    -1.92
     just
    -1.88
     whose
    -1.75
     by
    -1.73
     on
    -1.73
     and
    -1.71
     what
    -1.71
     before
    -1.70
    POSITIVE LOGITS
     этом
    1.62
     acuerdos
    1.59
     estos
    1.59
    。
    1.58
     باسلام
    1.55
     curtailed
    1.51
     améliorer
    1.51
     conocidos
    1.48
    の基本
    1.48
     сдела
    1.47
    Activations Density 0.001%

    No Known Activations