© 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. 9894
    Prev
    Next
    INDEX
    Explanations

    words starting with hyper

    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
     icône
    -1.71
     haja
    -1.59
    decoración
    -1.53
     ‘
    -1.52
    planted
    -1.52
     policiais
    -1.51
     folosi
    -1.49
     ‘‘
    -1.48
    彐
    -1.47
     need
    -1.45
    POSITIVE LOGITS
    item
    1.70
     seleccionadas
    1.64
     comienzan
    1.49
     podrían
    1.47
     навіть
    1.46
     $\
    1.41
     or
    1.38
    ix
    1.37
    x
    1.36
     даже
    1.34
    Activations Density 0.015%

    No Known Activations