© 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. 69204
    Prev
    Next
    INDEX
    Explanations

    alarms, security, and signals

    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
    (
    -1.31
    ou
    -1.28
    in
    -1.27
    j
    -1.27
    ?”
    -1.27
    c
    -1.25
     entrusted
    -1.20
    ang
    -1.19
     accustomed
    -1.16
    texpr
    -1.16
    POSITIVE LOGITS
    likleri
    1.48
     redaktion
    1.46
     originalen
    1.43
    الدرا
    1.40
     for
    1.40
    痦
    1.38
    washingtonpost
    1.38
     tiež
    1.36
    plush
    1.36
     asume
    1.35
    Activations Density 0.020%

    No Known Activations