© 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. 7253
    Prev
    Next
    INDEX
    Explanations

    feeling of shame

    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
    ៚
    -2.06
     škoda
    -1.96
    嵛
    -1.85
     actuales
    -1.84
    pegno
    -1.81
    presa
    -1.80
     lidé
    -1.77
    köy
    -1.77
     religiosos
    -1.75
     funguje
    -1.75
    POSITIVE LOGITS
    ↵
    2.30
    ed
    1.93
    ing
    1.79
    ↵↵
    1.69
     uan
    1.58
     december
    1.49
    </b>
    1.48
    faced
    1.48
     Jezus
    1.45
     maksimum
    1.45
    Activations Density 0.008%

    No Known Activations