© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 78108
    Prev
    Next
    INDEX
    Explanations

    proper nouns and numbers

    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
    Código
    -0.78
    承認
    -0.75
     normally
    -0.73
     見
    -0.71
    normally
    -0.71
    lichkeit
    -0.70
    particularly
    -0.70
    Direccion
    -0.70
     constitutes
    -0.69
    未来的
    -0.69
    POSITIVE LOGITS
     thinking
    0.94
     RAS
    0.75
     herds
    0.75
     erle
    0.74
     övers
    0.74
    瞌
    0.73
    纂
    0.73
     знаю
    0.72
     pund
    0.72
     ole
    0.72
    Activations Density 0.222%

    No Known Activations