© 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. 73565
    Prev
    Next
    INDEX
    Explanations

    scroll position

    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
    躋
    -1.93
    pausal
    -1.91
    Unfortunately
    -1.88
    </b>
    -1.86
    Interestingly
    -1.84
    Besides
    -1.82
    Those
    -1.81
     colorear
    -1.80
     resaltar
    -1.80
     メニュー
    -1.79
    POSITIVE LOGITS
    ↵
    2.09
     in
    1.98
     $
    1.83
     transferring
    1.78
     ’
    1.76
    л
    1.75
     став
    1.73
    蚴
    1.73
    I
    1.73
     jóvenes
    1.70
    Activations Density 0.022%

    No Known Activations