© 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. 10-GEMMASCOPE-RES-131K
    7. 7979
    Prev
    Next
    INDEX
    Explanations

    giving back or thanks

    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_10/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
     efektif
    -1.55
     about
    -1.39
    רו
    -1.38
     new
    -1.33
    意思是
    -1.32
    ！」
    -1.26
    　「
    -1.26
     our
    -1.24
     flä
    -1.23
    ("-",
    -1.21
    POSITIVE LOGITS
    
    1.32
    
    1.25
     mérit
    1.25
     semelh
    1.24
    hopefully
    1.21
     pourraient
    1.21
    ۔۔
    1.21
    unlike
    1.20
    somewhat
    1.20
     suscit
    1.20
    Activations Density 0.011%

    No Known Activations