© 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. 73260
    Prev
    Next
    INDEX
    Explanations

    state changes or updates

    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
     电脑
    -1.02
     佛
    -1.00
    etermined
    -0.98
     截图
    -0.94
     continuant
    -0.94
     ginge
    -0.93
    꿩
    -0.93
     épic
    -0.93
     插
    -0.93
    皙
    -0.93
    POSITIVE LOGITS
     changes
    1.31
     increase
    1.12
     change
    1.06
     changed
    1.05
     add
    1.04
     you
    1.04
     reset
    1.02
     new
    0.99
     cambiar
    0.93
     durch
    0.88
    Activations Density 0.002%

    No Known Activations