© 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. 13020
    Prev
    Next
    INDEX
    Explanations

    quantities of things

    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
    <bos>
    -1.32
     being
    -1.21
     to
    -1.13
     would
    -1.11
     campes
    -1.03
     doing
    -1.03
    ͎
    -1.03
     experience
    -1.02
    Generally
    -1.02
     providing
    -1.02
    POSITIVE LOGITS
     japonaise
    1.17
    corrhi
    1.16
    のマ
    1.09
     associée
    1.06
    Forgot
    1.06
    燜
    1.06
    灩
    1.05
     liée
    1.05
    tése
    1.05
     biela
    1.04
    Activations Density 0.179%

    No Known Activations