© 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. 22-GEMMASCOPE-RES-131K
    7. 27923
    Prev
    Next
    INDEX
    Explanations

    company statements

    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
    ẨM
    -1.00
    🧵
    -0.93
    jTable
    -0.91
     will
    -0.90
    fgaben
    -0.89
     通用
    -0.85
     kecuali
    -0.84
    nitř
    -0.82
    knowing
    -0.80
     monumento
    -0.79
    POSITIVE LOGITS
    確かに
    1.53
     our
    1.20
     indeed
    1.19
    确实
    1.11
    ığımız
    1.09
    的确
    1.09
     we
    1.00
     Indeed
    0.98
     issue
    0.97
    たしか
    0.97
    Activations Density 0.033%

    No Known Activations