© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 25673
    Prev
    Next
    INDEX
    Explanations

    lists of items

    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_22/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
    æld
    -0.91
    └──
    -0.88
     }}"
    -0.87
    ♎
    -0.85
    ؤول
    -0.83
    𝙃
    -0.81
     dolci
    -0.79
     querida
    -0.79
    ♏
    -0.79
     représentation
    -0.79
    POSITIVE LOGITS
     Middle
    0.89
    ph
    0.81
     Sot
    0.81
    ш
    0.78
     kecuali
    0.78
    ergies
    0.77
    UMIN
    0.77
     gemeinsam
    0.76
    ده
    0.76
     Mid
    0.76
    Activations Density 0.092%

    No Known Activations