© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 129566
    Prev
    Next
    INDEX
    Explanations

    Perth, Western Australia

    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
     úplně
    -1.02
    NewLabel
    -1.02
    ことなく
    -1.00
     complicada
    -0.98
    }></
    -0.96
    一顿
    -0.95
     구
    -0.93
     mêmes
    -0.92
    が無い
    -0.92
     circunstan
    -0.91
    POSITIVE LOGITS
     Seahawks
    1.23
     Seattle
    1.20
     Perth
    1.16
    Perth
    1.16
    Seattle
    1.15
    seattle
    1.09
     Spokane
    1.04
     WA
    1.03
     Sardin
    1.03
     Puget
    1.02
    Activations Density 0.019%

    No Known Activations