© 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. 44649
    Prev
    Next
    INDEX
    Explanations

    Java class names `JFrame`, `QString`, `HashSet`

    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
     That
    -2.95
    But
    -2.48
     Как
    -2.45
     Many
    -2.44
     Most
    -2.42
     Used
    -2.41
     Sometimes
    -2.36
     Didn
    -2.34
     После
    -2.33
     steadfast
    -2.31
    POSITIVE LOGITS
    峮
    2.75
    ='".$
    2.50
    ]^{-
    2.47
    ୈ
    2.45
    錒
    2.44
    霂
    2.38
    一亮
    2.36
     från
    2.33
    ꯳
    2.33
    镚
    2.30
    Activations Density 0.002%

    No Known Activations