© 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. 22-GEMMASCOPE-RES-131K
    7. 25723
    Prev
    Next
    INDEX
    Explanations

    list closing punctuation

    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_22/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
     ۱۴۰۰
    -0.99
     Similarly
    -0.86
    年
    -0.84
    지
    -0.84
    else
    -0.83
     are
    -0.83
    ender
    -0.82
     With
    -0.82
    plant
    -0.82
    وم
    -0.82
    POSITIVE LOGITS
     optimizar
    1.20
    :"#
    1.06
    境的
    0.98
     PUSTAKA
    0.96
    Минусы
    0.96
    歎
    0.95
     povezave
    0.93
    Waga
    0.93
    ובה
    0.91
    Krankheitsbild
    0.90
    Activations Density 0.004%

    No Known Activations