© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 104254
    Prev
    Next
    INDEX
    Explanations

    Apache License 2.0

    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
     itinéraires
    -1.94
     séjours
    -1.90
    *"
    -1.89
     alkoh
    -1.88
    
    -1.84
    "-"
    -1.79
    <$
    -1.78
     élections
    -1.77
     nouveautés
    -1.77
    >
    -1.76
    POSITIVE LOGITS
    B
    2.45
    N
    2.27
    V
    2.22
    J
    2.14
     speziellen
    2.09
    M
    2.08
    のお話
    2.06
    C
    2.03
    S
    1.98
    T
    1.98
    Activations Density 0.045%

    No Known Activations