© 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. 22-GEMMASCOPE-RES-131K
    7. 72660
    Prev
    Next
    INDEX
    Explanations

    factors contributing to outcomes

    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_22/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
    ֵי
    -0.99
    第八
    -0.99
     forskellige
    -0.98
    ՝
    -0.94
    Ingredienti
    -0.93
     ۱۸
    -0.92
     ۱۴
    -0.92
     sekitarnya
    -0.91
    рованы
    -0.90
     tertentu
    -0.90
    POSITIVE LOGITS
     explanation
    1.18
     account
    1.18
     factor
    1.15
     contributor
    1.12
     contribution
    1.12
     accounted
    1.09
     cyclisme
    1.08
     explain
    1.07
     contributions
    1.07
     alone
    1.06
    Activations Density 0.136%

    No Known Activations