© 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. 60164
    Prev
    Next
    INDEX
    Explanations

    special characters and code

    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
    顒
    -3.08
     незавер
    -3.02
    ſſen
    -3.00
    鼷
    -2.97
    ⎽
    -2.97
    ᭝
    -2.78
    铼
    -2.77
    秝
    -2.75
    瀦
    -2.75
    حياته
    -2.75
    POSITIVE LOGITS
    ing
    3.95
    ’
    3.52
     \"
    3.20
     '
    3.06
     -
    2.98
    ed
    2.70
     …
    2.67
    TAKE
    2.63
    颪
    2.56
     пять
    2.53
    Activations Density 0.000%

    No Known Activations