© 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. 10-GEMMASCOPE-RES-131K
    7. 85918
    Prev
    Next
    INDEX
    Explanations

    stuck in

    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
     possa
    -1.73
     titolata
    -1.67
    鉿
    -1.55
     diki
    -1.55
     menek
    -1.55
    側から
    -1.54
    蛻
    -1.53
    勦
    -1.53
     całą
    -1.52
     umana
    -1.52
    POSITIVE LOGITS
    {~
    1.99
    in
    1.66
     identifies
    1.65
    ]}$
    1.61
     leider
    1.57
    PerformLayout
    1.55
     使っ
    1.55
     Currently
    1.54
    нів
    1.52
    )),
    1.52
    Activations Density 0.016%

    No Known Activations