© 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. 129448
    Prev
    Next
    INDEX
    Explanations

    Milton Freewater

    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
    fass
    -0.96
     maintien
    -0.94
    alable
    -0.94
    
    -0.93
    私たちは
    -0.91
    setMin
    -0.90
    unfortunately
    -0.90
     ਫ
    -0.90
    Wireless
    -0.89
     schuldig
    -0.89
    POSITIVE LOGITS
     that
    1.45
     other
    1.18
     one
    1.10
     what
    1.08
     at
    1.05
     after
    1.03
     could
    0.95
     February
    0.95
     almost
    0.94
     by
    0.93
    Activations Density 0.166%

    No Known Activations