© 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. 113463
    Prev
    Next
    INDEX
    Explanations

    decisions based on

    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
    ONLY
    -1.67
     Otras
    -1.54
     poden
    -1.52
     ſtill
    -1.50
     فقط
    -1.48
    푉
    -1.47
    ⻬
    -1.45
    beten
    -1.43
     Otros
    -1.40
     És
    -1.40
    POSITIVE LOGITS
     about
    2.19
     this
    2.13
     decisions
    1.99
     that
    1.92
     decide
    1.82
    Decisions
    1.75
     decision
    1.72
     decided
    1.70
     these
    1.70
     decides
    1.67
    Activations Density 0.066%

    No Known Activations