© 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. 60122
    Prev
    Next
    INDEX
    Explanations

    copyright notices, licenses, and citations

    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
     for
    -1.20
     and
    -1.14
     each
    -1.13
     geïsole
    -1.09
     after
    -1.09
     with
    -1.07
     סס
    -1.04
     has
    -1.02
     will
    -1.01
     on
    -1.00
    POSITIVE LOGITS
     של
    1.28
     ש
    1.27
     ו
    1.27
     ב
    1.22
     פ
    1.17
     regel
    1.16
     ד
    1.16
     ห
    1.16
     ג
    1.15
     serene
    1.14
    Activations Density 0.002%

    No Known Activations