© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 13135
    Prev
    Next
    INDEX
    Explanations

    objects breaking or getting stuck

    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
    然后再
    -1.03
     dúvidas
    -0.93
     that
    -0.93
    🎷
    -0.93
    地产
    -0.91
    ḿ
    -0.91
     във
    -0.90
     туры
    -0.89
     quenched
    -0.88
    ))/(
    -0.87
    POSITIVE LOGITS
    volent
    1.22
     become
    1.13
    ícias
    1.05
    ternut
    1.05
     several
    1.02
    Удачи
    1.00
    :"-
    0.99
     bị
    0.98
     varias
    0.97
    Verlag
    0.97
    Activations Density 0.025%

    No Known Activations