© 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. 129120
    Prev
    Next
    INDEX
    Explanations

    copyright notices

    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
     Temperatura
    -1.38
     almohada
    -1.36
    苤
    -1.33
     ciutat
    -1.33
     parede
    -1.33
     pesso
    -1.33
     praça
    -1.32
     Konkur
    -1.31
    duled
    -1.29
     garrafa
    -1.29
    POSITIVE LOGITS
     by
    1.66
     or
    1.62
    Following
    1.42
     with
    1.41
     -
    1.39
    Those
    1.38
     !!!
    1.34
    just
    1.31
    Every
    1.28
     /
    1.27
    Activations Density 0.151%

    No Known Activations