© 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. 43288
    Prev
    Next
    INDEX
    Explanations

    loose, loosen, loosely

    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
    ICOLON
    -2.17
    巂
    -1.96
     beijo
    -1.91
    鈈
    -1.88
     pemeriksaan
    -1.81
    書いて
    -1.77
    嵛
    -1.76
    VING
    -1.75
    霎
    -1.75
    鐒
    -1.74
    POSITIVE LOGITS
     $
    2.31
    }
    2.17
    !"
    2.16
    2
    2.13
    \
    1.98
    Merkmale
    1.89
    8
    1.85
     loose
    1.83
    ER
    1.79
    IANGLES
    1.77
    Activations Density 0.007%

    No Known Activations