© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 25974
    Prev
    Next
    INDEX
    Explanations

    Leo, Leon, Lion

    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_34/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
     commemorate
    -0.78
    istes
    -0.77
    Rounded
    -0.76
     Paz
    -0.75
    备案
    -0.73
    INTEGR
    -0.72
     Archaeology
    -0.72
    ственно
    -0.72
     cleanse
    -0.72
     carrot
    -0.70
    POSITIVE LOGITS
     Lion
    1.02
     LION
    0.99
    獅
    0.97
    Lion
    0.91
    leos
    0.91
     Лео
    0.88
     Leo
    0.88
    Leo
    0.82
     overall
    0.80
     along
    0.79
    Activations Density 0.018%

    No Known Activations