© 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. 12861
    Prev
    Next
    INDEX
    Explanations

    JavaScript element selection

    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
     at
    -1.16
     bestäm
    -1.08
     and
    -0.98
     äls
    -0.98
     through
    -0.96
    なんだろう
    -0.96
     without
    -0.95
    Ꮐ
    -0.94
     probably
    -0.93
     anvä
    -0.93
    POSITIVE LOGITS
     „
    1.15
     gouvern
    0.98
     Système
    0.97
     pérd
    0.97
    のですか
    0.96
    头的
    0.96
     poë
    0.95
    öffentlichung
    0.95
     białym
    0.94
    carro
    0.94
    Activations Density 0.031%

    No Known Activations