© 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. 69439
    Prev
    Next
    INDEX
    Explanations

    forecasting future events

    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
    नलोड
    -3.05
    quierda
    -2.48
    𖥧
    -2.42
     Для
    -2.39
    ଢ
    -2.36
    ᾐ
    -2.34
    ୌ
    -2.25
     Когда
    -2.23
     sarcastic
    -2.22
    ндарт
    -2.20
    POSITIVE LOGITS
    '
    4.00
     “
    2.89
    to
    2.70
    x
    2.69
    ная
    2.64
    le
    2.41
    l
    2.31
    ers
    2.22
    。“
    2.16
    ↵
    2.14
    Activations Density 0.003%

    No Known Activations