© 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. 25893
    Prev
    Next
    INDEX
    Explanations

    you can learn

    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
     должны
    -0.97
     всички
    -0.94
     debes
    -0.94
     WERE
    -0.94
    aternity
    -0.94
     generaciones
    -0.93
     devons
    -0.90
     beiden
    -0.89
     являются
    -0.88
    都要
    -0.87
    POSITIVE LOGITS
     can
    1.25
     no
    1.20
     benefit
    1.19
     never
    1.13
     not
    1.13
    literally
    1.01
    benefit
    1.01
     máte
    0.99
     doesn
    0.98
     gets
    0.96
    Activations Density 0.050%

    No Known Activations