© 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. 34-GEMMASCOPE-RES-131K
    7. 70311
    Prev
    Next
    INDEX
    Explanations

    selected or optional choices

    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_34/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
    ICEF
    -0.91
    CMOS
    -0.86
    delaide
    -0.85
    ZING
    -0.81
    珐
    -0.80
    矫
    -0.78
    茯
    -0.77
    WiFi
    -0.75
     audition
    -0.75
    geord
    -0.75
    POSITIVE LOGITS
     will
    1.10
     selected
    1.01
    Selected
    0.98
    Optional
    0.91
    Choice
    0.88
     standard
    0.87
    selected
    0.85
     Choice
    0.84
     except
    0.82
     zostanie
    0.82
    Activations Density 0.008%

    No Known Activations