© 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. 123852
    Prev
    Next
    INDEX
    Explanations

    ag

    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
    逦
    -3.03
    珵
    -2.52
    る
    -2.30
    阗
    -2.27
    ()}>
    -2.22
    ឵
    -2.20
     hígado
    -2.19
    felpa
    -2.17
    也将
    -2.11
    窳
    -2.11
    POSITIVE LOGITS
    ag
    4.34
    c
    2.95
    D
    2.80
    g
    2.73
    ay
    2.47
    um
    2.45
    也许
    2.42
    ap
    2.41
    X
    2.39
    ྃ
    2.38
    Activations Density 0.018%

    No Known Activations