© 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. 22-GEMMASCOPE-RES-131K
    7. 79968
    Prev
    Next
    INDEX
    Explanations

    lists and conjunctions

    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
     ontwerp
    -1.51
     combattre
    -1.38
    approximately
    -1.38
     apparaître
    -1.37
     Nguy
    -1.29
     diminuer
    -1.28
    ditionally
    -1.28
    コチラ
    -1.27
    poptotic
    -1.23
     ongeveer
    -1.23
    POSITIVE LOGITS
     kecelakaan
    1.38
     even
    1.30
     all
    1.13
    各種
    1.12
     ....
    1.12
    鮪
    1.11
     nuova
    1.10
     for
    1.09
     .....
    1.08
     особли
    1.07
    Activations Density 0.011%

    No Known Activations