© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 104141
    Prev
    Next
    INDEX
    Explanations

    packing or stuffing things

    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
    ❕
    -1.99
     žaid
    -1.99
    🌟
    -1.81
    ⁛
    -1.74
     教程
    -1.74
    💚
    -1.73
     abstracta
    -1.72
     interpretar
    -1.72
     virš
    -1.72
     nocturna
    -1.71
    POSITIVE LOGITS
    ()]);
    1.96
    1
    1.94
    </b>
    1.74
     *
    1.67
    5
    1.65
    ),
    1.61
    <bos>
    1.59
     info
    1.57
    ?
    1.54
    ).
    1.51
    Activations Density 0.015%

    No Known Activations