© 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. 34-GEMMASCOPE-RES-131K
    7. 84961
    Prev
    Next
    INDEX
    Explanations

    license file comments

    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
     rod
    -0.90
    ône
    -0.77
    ッド
    -0.74
    Exceptional
    -0.74
     onCreateView
    -0.73
    atology
    -0.73
     POT
    -0.72
     dayan
    -0.71
     Chan
    -0.70
    marginBottom
    -0.70
    POSITIVE LOGITS
     otherwise
    0.77
     Opium
    0.75
     reckoned
    0.74
     reckoning
    0.73
     plenamente
    0.73
     facilitar
    0.72
     apagar
    0.72
    dientes
    0.70
     pesanan
    0.70
    suz
    0.69
    Activations Density 0.004%

    No Known Activations