© 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. 22-GEMMASCOPE-RES-131K
    7. 69262
    Prev
    Next
    INDEX
    Explanations

    market sector performance forecasts

    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_22/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
     Unterrichts
    -1.50
     mochilas
    -1.48
     hábit
    -1.44
     lámparas
    -1.39
     Erziehung
    -1.38
     placas
    -1.37
     你
    -1.34
     cortinas
    -1.34
    Ɍ
    -1.34
     nutzt
    -1.30
    POSITIVE LOGITS
     forecasts
    1.63
     forecast
    1.62
    ּוֹ
    1.52
    ἂ
    1.48
    :
    1.45
     market
    1.42
     investors
    1.38
     sector
    1.36
     analysts
    1.32
     growth
    1.31
    Activations Density 0.034%

    No Known Activations