© 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. 76263
    Prev
    Next
    INDEX
    Explanations

    outlook, forecast, prognosis

    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
     Diſ
    -0.84
    Ahol
    -0.83
    тии
    -0.82
    zili
    -0.82
    vertre
    -0.81
    verstanden
    -0.81
     solides
    -0.81
    alisme
    -0.80
    gebraucht
    -0.80
    verschluss
    -0.79
    POSITIVE LOGITS
     outlook
    6.00
     Outlook
    4.16
    outlook
    4.06
    Outlook
    3.97
     prospects
    3.31
     forecast
    2.83
     prognosis
    2.80
     prospect
    2.38
    展望
    2.22
     forecasts
    2.20
    Activations Density 0.041%

    No Known Activations