© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 99325
    Prev
    Next
    INDEX
    Explanations

    continue actions

    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
     появилась
    -1.00
    playera
    -0.92
    ριά
    -0.90
    Masukkan
    -0.90
    delion
    -0.89
    Зно
    -0.88
    gemeins
    -0.87
    啕
    -0.87
    ättä
    -0.86
    Fotó
    -0.86
    POSITIVE LOGITS
     continue
    9.13
     continues
    8.00
    continue
    7.97
     continued
    7.69
     continuing
    7.25
    继续
    6.88
     продолжа
    6.16
     continuar
    5.94
    繼續
    5.91
     Continue
    5.84
    Activations Density 0.437%

    No Known Activations