© 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. 8324
    Prev
    Next
    INDEX
    Explanations

    cities and festivals

    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
    2
    -2.83
    4
    -2.70
    甚至
    -2.52
    6
    -2.50
    1
    -2.48
    ーす
    -2.48
    也沒
    -2.44
    蟜
    -2.44
    
    -2.39
    3
    -2.22
    POSITIVE LOGITS
    龊
    2.61
    </strong>
    2.47
    痿
    2.41
     tetapi
    2.31
    e
    2.11
    あります
    2.11
    ࿙
    2.08
    酯
    2.05
     aloj
    2.03
     sedikit
    2.02
    Activations Density 0.001%

    No Known Activations