© 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. 105420
    Prev
    Next
    INDEX
    Explanations

    proper nouns and city names

    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
    鉭
    -2.34
    ︕
    -2.33
    骡
    -2.33
    with
    -2.28
    this
    -2.17
    sió
    -2.08
    .
    -2.08
    増えて
    -2.08
    鲠
    -2.03
    檮
    -2.03
    POSITIVE LOGITS
    S
    3.17
    B
    2.70
    (
    2.55
    L
    2.55
    F
    2.48
    V
    2.39
    R
    2.34
    P
    2.34
    O
    2.28
    W
    2.28
    Activations Density 0.075%

    No Known Activations