© 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. 8026
    Prev
    Next
    INDEX
    Explanations

    legal proceedings and court cases

    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
     henne
    -1.00
     Principe
    -0.99
    ÜN
    -0.99
     лишь
    -0.98
    Opere
    -0.97
     mek
    -0.97
     hende
    -0.95
    tuale
    -0.94
     with
    -0.94
     maroc
    -0.94
    POSITIVE LOGITS
     your
    1.45
     everything
    1.20
    goers
    1.18
     recomendada
    1.13
     senador
    1.13
     všechno
    1.10
    ’
    1.09
    徨
    1.07
     their
    1.06
    TUAL
    1.06
    Activations Density 0.114%

    No Known Activations