© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 12501
    Prev
    Next
    INDEX
    Explanations

    students voted

    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
     this
    -1.29
    これを
    -1.10
    diğimiz
    -1.09
     or
    -1.09
     our
    -1.05
     these
    -1.02
     farbe
    -1.01
     lyder
    -0.96
     Krá
    -0.95
     {};
    -0.91
    POSITIVE LOGITS
     conseguiu
    1.23
     começou
    1.09
     anunciou
    1.08
     celor
    1.08
    了一个
    1.05
     mostrou
    1.02
     explicou
    1.01
     informou
    1.01
     pediu
    1.00
     היא
    0.99
    Activations Density 0.001%

    No Known Activations