© 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. 28361
    Prev
    Next
    INDEX
    Explanations

    express worry about doing

    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
     icônes
    -1.32
     シリーズ
    -1.22
     défis
    -1.18
     Bibliote
    -1.17
    жні
    -1.16
    ECK
    -1.16
     acheteurs
    -1.14
    📅
    -1.14
     giúp
    -1.13
     seraient
    -1.11
    POSITIVE LOGITS
     or
    2.09
     there
    1.59
     whether
    1.53
     who
    1.33
     will
    1.33
     any
    1.29
     of
    1.27
     или
    1.27
     which
    1.23
     getting
    1.22
    Activations Density 0.014%

    No Known Activations