© 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. 22-GEMMASCOPE-RES-131K
    4. 73650
    Prev
    Next
    INDEX
    Explanations

    Samsung, Characterization, Unaltered

    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
     দেখ
    -0.99
     ولكن
    -0.95
     talvez
    -0.94
     других
    -0.94
     窗
    -0.94
    folie
    -0.91
    ENZO
    -0.91
     Theologie
    -0.90
     Politiker
    -0.90
    男朋友
    -0.90
    POSITIVE LOGITS
     this
    1.27
     you
    1.25
     podczas
    1.04
    اصر
    0.97
     during
    0.95
    原來
    0.94
    個月
    0.91
    あなたは
    0.91
     we
    0.90
    here
    0.90
    Activations Density 0.002%

    No Known Activations