© 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. 128517
    Prev
    Next
    INDEX
    Explanations

    dates and names

    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
     when
    -1.42
    fch
    -1.33
    再来
    -1.32
     because
    -1.29
    lahraga
    -1.26
    </strong>
    -1.26
     fós
    -1.24
    มากๆ
    -1.22
     also
    -1.22
    激烈
    -1.20
    POSITIVE LOGITS
    ]
    1.52
    ,,
    1.49
    ,(
    1.43
     momentan
    1.42
     Pflanze
    1.39
    ."
    1.37
    
    1.34
     десять
    1.34
    )
    1.30
    謌
    1.29
    Activations Density 0.024%

    No Known Activations