© 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. 78228
    Prev
    Next
    INDEX
    Explanations

    duration and time

    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
     five
    -1.20
     four
    -1.16
     hours
    -1.15
     Five
    -1.06
    Four
    -1.05
    Five
    -1.05
     Four
    -1.03
    Hours
    -1.02
     ten
    -0.99
     fifteen
    -0.98
    POSITIVE LOGITS
     ninety
    1.36
     sixty
    1.09
     seventy
    1.08
    Nin
    1.08
     Ninety
    1.05
     Sixty
    0.98
     ۱
    0.95
     Seventy
    0.94
    fifty
    0.94
     One
    0.90
    Activations Density 0.030%

    No Known Activations