© 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. 10-GEMMASCOPE-RES-131K
    7. 80837
    Prev
    Next
    INDEX
    Explanations

    underscores followed by identifiers

    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
     today
    -1.38
     instead
    -1.33
     or
    -1.32
    および
    -1.30
     what
    -1.29
     how
    -1.26
    y
    -1.21
     now
    -1.20
    などは
    -1.20
     besonder
    -1.16
    POSITIVE LOGITS
    einer
    1.70
    einem
    1.69
    卧槽
    1.45
    啊啊
    1.43
    лое
    1.40
     Genel
    1.39
    大人気
    1.38
    喽
    1.38
     fenti
    1.35
    跻
    1.35
    Activations Density 0.006%

    No Known Activations