© 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. 75685
    Prev
    Next
    INDEX
    Explanations

    with open

    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
     to
    -2.28
     początku
    -1.73
     who
    -1.57
     hlavy
    -1.52
     depois
    -1.49
     poté
    -1.49
    ではある
    -1.48
    罍
    -1.47
     śnie
    -1.45
     가지
    -1.43
    POSITIVE LOGITS
    There
    2.19
    It
    1.91
    This
    1.84
     For
    1.77
     двумя
    1.71
    They
    1.70
    ]')
    1.66
    Kedua
    1.65
    是吗
    1.59
     forState
    1.57
    Activations Density 0.003%

    No Known Activations