© 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. 67608
    Prev
    Next
    INDEX
    Explanations

    code path imports

    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
    矬
    -1.59
     adquirido
    -1.52
     asegurado
    -1.50
    gefügt
    -1.48
     propósitos
    -1.44
     gebruikt
    -1.42
     retirado
    -1.42
     devastation
    -1.41
     rů
    -1.41
     kotlinx
    -1.39
    POSITIVE LOGITS
    This
    2.06
    They
    1.95
    </em>
    1.90
    It
    1.78
    7
    1.60
     This
    1.59
    </h4>
    1.58
    4
    1.55
     You
    1.53
     Being
    1.48
    Activations Density 0.001%

    No Known Activations