© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 30839
    Prev
    Next
    INDEX
    Explanations

    compared, versus, or, but

    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
    Especially
    -1.21
     notamment
    -1.20
    特に
    -1.18
     особенно
    -1.14
    〢
    -1.13
    especially
    -1.11
     Soporte
    -1.10
    pecially
    -1.10
    particularly
    -1.09
     bernama
    -1.08
    POSITIVE LOGITS
     compared
    2.27
     or
    2.14
     which
    1.97
     far
    1.81
     while
    1.76
     and
    1.75
     with
    1.71
     equivalent
    1.66
     versus
    1.57
     but
    1.52
    Activations Density 0.073%

    No Known Activations