© 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. 34-GEMMASCOPE-RES-131K
    7. 58775
    Prev
    Next
    INDEX
    Explanations

    distributed under license

    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
     COMPOUNDS
    -1.09
    tobe
    -1.05
    centerY
    -0.97
     TECHNOLOGIES
    -0.96
    brews
    -0.96
     onOptions
    -0.96
    +
    -0.96
    cto
    -0.96
     Arzne
    -0.96
    chage
    -0.94
    POSITIVE LOGITS
    Один
    0.90
     Dermatologist
    0.87
    里面的
    0.86
     bushel
    0.84
     multiverse
    0.82
     Rugged
    0.81
     MEA
    0.81
    音频
    0.80
     Chlorine
    0.79
    Ema
    0.79
    Activations Density 0.002%

    No Known Activations