© 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. 130925
    Prev
    Next
    INDEX
    Explanations

    cars

    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
    
    -3.34
    蟜
    -3.20
    0
    -3.11
     behulp
    -2.72
     帅气
    -2.55
    驁
    -2.48
    鲣
    -2.45
    蕺
    -2.45
    ではまた
    -2.44
    幾天
    -2.44
    POSITIVE LOGITS
    s
    4.81
    n
    3.03
    y
    2.92
    h
    2.89
    is
    2.73
    t
    2.70
    te
    2.64
    w
    2.52
    所有人都
    2.52
    ti
    2.52
    Activations Density 0.002%

    No Known Activations