© 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. 111214
    Prev
    Next
    INDEX
    Explanations

    university or college related terms

    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
    饪
    -2.11
    ⭓
    -2.00
    盉
    -1.98
     acceptez
    -1.91
     Spanyol
    -1.89
     GOtt
    -1.88
     It
    -1.88
    𖥧
    -1.87
     faço
    -1.86
    !')
    -1.84
    POSITIVE LOGITS
    7
    1.81
     assistant
    1.78
     indiscriminate
    1.75
    8
    1.74
    in
    1.73
    ࿚
    1.73
    ’
    1.65
     кі
    1.64
    3
    1.64
     artful
    1.63
    Activations Density 0.005%

    No Known Activations