© 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. 84909
    Prev
    Next
    INDEX
    Explanations

    cleared or guilty

    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
    跸
    -2.23
    先生が
    -1.85
     nejlepší
    -1.81
    硖
    -1.70
     हैं
    -1.70
    矬
    -1.68
    勦
    -1.68
     deine
    -1.64
    </h3>
    -1.63
     actividades
    -1.63
    POSITIVE LOGITS
    ’
    2.70
    ↵
    2.42
    This
    2.03
    On
    1.83
    While
    1.81
    At
    1.77
    }$
    1.75
    }$.
    1.74
     ハ
    1.70
    Despite
    1.70
    Activations Density 0.005%

    No Known Activations