© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 38594
    Prev
    Next
    INDEX
    Explanations

    places and descriptions

    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
    犷
    -1.30
    thodox
    -1.13
    alucía
    -1.08
    輛
    -1.08
     รุ่น
    -1.04
     Departement
    -1.04
    ệp
    -1.03
    ponible
    -1.03
     XXXIV
    -1.02
     yapmak
    -1.01
    POSITIVE LOGITS
     elsewhere
    1.59
     here
    1.23
     places
    1.13
    卡通
    1.03
     so
    1.03
    ｀)
    1.02
    وفي
    1.01
     overall
    1.00
    Similar
    0.99
     similar
    0.98
    Activations Density 0.012%

    No Known Activations