© 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. 65941
    Prev
    Next
    INDEX
    Explanations

    tour of

    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
     you
    -1.45
     
    -1.30
     or
    -1.18
     here
    -0.96
     this
    -0.95
    的价格
    -0.94
    了些
    -0.94
    ソナ
    -0.94
     according
    -0.91
    ξ
    -0.91
    POSITIVE LOGITS
    recently
    1.38
    erobic
    1.38
     recently
    1.34
    cestry
    1.29
    alisis
    1.29
     how
    1.27
     facilities
    1.25
    Aktu
    1.25
     renovar
    1.21
    Dobrý
    1.15
    Activations Density 0.030%

    No Known Activations