© 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. 38995
    Prev
    Next
    INDEX
    Explanations

    challenge others or ideas

    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
     கு
    -0.96
     lác
    -0.90
     Ву
    -0.85
     hí
    -0.84
     muft
    -0.83
     начать
    -0.82
    gradation
    -0.80
     urme
    -0.79
    евский
    -0.79
     helpful
    -0.78
    POSITIVE LOGITS
     challenge
    1.43
     Challenge
    1.27
    challenge
    1.27
    Challenge
    1.16
     Challenging
    1.09
    challenged
    1.09
     challenged
    1.07
     CHALLENGE
    0.99
     kysy
    0.98
     challenging
    0.97
    Activations Density 0.036%

    No Known Activations