© 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. 85599
    Prev
    Next
    INDEX
    Explanations

    URLs and website paths

    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
     расположен
    -1.45
     unange
    -1.34
    ficulties
    -1.32
     nachfol
    -1.30
     Большая
    -1.30
    
    -1.29
     sicheren
    -1.29
    來
    -1.28
     schnellen
    -1.27
    してくれる
    -1.27
    POSITIVE LOGITS
    »:
    1.58
    ”).
    1.57
     =
    1.56
    ?」
    1.49
    ”:
    1.45
     oliveira
    1.38
     femin
    1.38
     a
    1.36
     marte
    1.36
     menta
    1.35
    Activations Density 0.023%

    No Known Activations