© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 69073
    Prev
    Next
    INDEX
    Explanations

    life events and people

    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
    Several
    -1.51
    There
    -1.50
    Unlike
    -1.45
    What
    -1.45
    hamed
    -1.41
     two
    -1.37
     Several
    -1.36
    although
    -1.36
     AppColors
    -1.34
     but
    -1.31
    POSITIVE LOGITS
    ATIONAL
    1.41
     your
    1.40
     }).
    1.31
     Atención
    1.30
     meto
    1.29
     my
    1.29
    𓁹
    1.29
     Dinas
    1.27
    émie
    1.26
    れてる
    1.25
    Activations Density 0.082%

    No Known Activations