© 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. 22-GEMMASCOPE-RES-131K
    7. 128284
    Prev
    Next
    INDEX
    Explanations

    variable pointers

    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
    などを
    -1.96
    など
    -1.41
    <bos>
    -1.35
    などで
    -1.34
    では
    -1.30
     normalen
    -1.30
     sucede
    -1.27
     considerando
    -1.27
    なども
    -1.27
    と
    -1.27
    POSITIVE LOGITS
    When
    1.48
    ၀
    1.40
    Even
    1.37
     Politica
    1.35
    During
    1.35
     Jardim
    1.34
    んですけど
    1.30
    There
    1.29
    ‪.‬‬
    1.28
    Название
    1.27
    Activations Density 0.003%

    No Known Activations