© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 15348
    Prev
    Next
    INDEX
    Explanations

    university names

    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
     vulné
    -1.75
    洌
    -1.74
     combustível
    -1.72
     .......
    -1.71
     !!!!
    -1.69
     aboli
    -1.67
    鬭
    -1.66
    锱
    -1.64
    䜣
    -1.63
     และ
    -1.61
    POSITIVE LOGITS
    Only
    2.50
    Just
    2.38
    During
    2.36
    There
    2.31
    One
    2.25
     of
    2.19
    After
    2.14
    Because
    2.13
    s
    2.09
    Through
    2.08
    Activations Density 0.015%

    No Known Activations