© 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. 99850
    Prev
    Next
    INDEX
    Explanations

    Windows registry and group policy

    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
    ens
    -1.58
    ?
    -1.53
     was
    -1.51
    戋
    -1.46
    "
    -1.45
    ol
    -1.44
    est
    -1.40
    led
    -1.39
    î
    -1.39
        
    -1.36
    POSITIVE LOGITS
    鴣
    1.69
    ၟ
    1.58
    瑧
    1.55
    wać
    1.45
    ᩠
    1.44
    商品説明
    1.43
     dotyczące
    1.41
     mówią
    1.38
     Meilleures
    1.38
     dirit
    1.38
    Activations Density 0.021%

    No Known Activations