© 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. 128135
    Prev
    Next
    INDEX
    Explanations

    positive suggestions and hopes

    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
    ceptable
    -1.05
    װ
    -1.02
     its
    -1.01
     אבל
    -0.98
    یات
    -0.94
    яд
    -0.93
    [
    -0.92
    entwick
    -0.91
    ないけど
    -0.91
    explique
    -0.90
    POSITIVE LOGITS
     help
    1.23
     giúp
    1.22
     like
    1.18
     hopefully
    1.18
     thereby
    1.17
     always
    1.16
     these
    1.15
     solche
    1.15
     mutual
    1.09
     eventually
    1.09
    Activations Density 0.022%

    No Known Activations