© 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. 58470
    Prev
    Next
    INDEX
    Explanations

    note that

    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
     freaking
    -1.55
    )}>
    -1.46
    日閲覧
    -1.38
    就不能
    -1.37
    だよ
    -1.36
    和谐
    -1.34
     nearby
    -1.33
     cualquier
    -1.31
     dichas
    -1.31
    <bos>
    -1.30
    POSITIVE LOGITS
     truk
    1.85
    pired
    1.79
     sepak
    1.78
     merke
    1.75
     berge
    1.73
    8
    1.71
     fabrik
    1.71
     lenge
    1.70
    joyed
    1.67
     réalisateur
    1.66
    Activations Density 0.021%

    No Known Activations