© 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. 20756
    Prev
    Next
    INDEX
    Explanations

    CG graphics programming

    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
     That
    -1.73
     intoxicating
    -1.52
    缡
    -1.49
    ائح
    -1.48
    畊
    -1.47
     PARTE
    -1.47
     venga
    -1.47
     influencing
    -1.46
     thinks
    -1.46
     adds
    -1.46
    POSITIVE LOGITS
    橚
    1.68
    ↵
    1.63
     chapéu
    1.60
     braço
    1.59
    鬟
    1.58
     peito
    1.56
     opět
    1.55
    ]
    1.55
     capuz
    1.55
     pescoço
    1.55
    Activations Density 0.001%

    No Known Activations