© 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. 60509
    Prev
    Next
    INDEX
    Explanations

    advertising and ads

    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
    愎
    -2.34
    ”,
    -2.33
    vantaged
    -2.19
    而又
    -2.09
    ’,
    -1.95
    ,’’
    -1.94
    ),
    -1.91
    Ⲉ
    -1.89
    }
    -1.88
    。「
    -1.87
    POSITIVE LOGITS
    靦
    1.98
    </i>
    1.91
    蟊
    1.88
    釙
    1.85
    還好
    1.84
    よかった
    1.82
    廛
    1.78
     freaking
    1.77
     distintos
    1.76
    1.75
    Activations Density 0.010%

    No Known Activations