© 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. 81035
    Prev
    Next
    INDEX
    Explanations

    Acc followed by ra, laim, ur, um, or parallel

    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
     コミック
    -0.88
     erklä
    -0.88
     Zuz
    -0.85
    loroethane
    -0.82
    アニメ
    -0.82
     味
    -0.79
     Reglamento
    -0.79
     he
    -0.78
     若
    -0.78
    (
    -0.77
    POSITIVE LOGITS
     ACC
    1.74
    acc
    1.52
     Acc
    1.50
     acc
    1.45
    Acc
    1.41
    ACC
    1.30
     predstav
    0.93
    Klima
    0.90
    要么
    0.89
     Accu
    0.88
    Activations Density 0.025%

    No Known Activations