© 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. 10-GEMMASCOPE-RES-131K
    7. 7380
    Prev
    Next
    INDEX
    Explanations

    still... later

    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_10/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
     algún
    -1.43
     actualmente
    -1.39
     continually
    -1.34
     empêcher
    -1.34
     verbund
    -1.34
     recently
    -1.33
     primero
    -1.30
     récemment
    -1.30
    recently
    -1.30
    particularly
    -1.29
    POSITIVE LOGITS
     still
    1.43
    Still
    1.26
     three
    1.10
     two
    1.09
     how
    1.09
    InMillis
    1.07
     ещё
    1.02
    énéral
    1.02
     еще
    1.01
     Weisheit
    1.00
    Activations Density 0.128%

    No Known Activations