© 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. 15067
    Prev
    Next
    INDEX
    Explanations

    counts or quantities

    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
    }
    -2.50
     {
    -2.20
     glimpses
    -2.19
    𐌳
    -2.11
     Może
    -2.08
     Bardzo
    -2.02
    ]
    -1.98
     Dzięki
    -1.91
    )
    -1.91
     Jednak
    -1.90
    POSITIVE LOGITS
    d
    2.08
    鸲
    1.95
    ㋛
    1.91
     として
    1.88
     endDate
    1.87
    虓
    1.85
    塒
    1.77
    鶫
    1.77
    嘥
    1.74
     兄弟
    1.73
    Activations Density 0.006%

    No Known Activations