© 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. 79608
    Prev
    Next
    INDEX
    Explanations

    non-english words or characters

    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
     twa
    -1.03
     WRX
    -1.02
     Boletín
    -0.99
     )(
    -0.98
     tts
    -0.98
     sts
    -0.96
     Badan
    -0.96
     noo
    -0.96
     Xt
    -0.95
     cj
    -0.95
    POSITIVE LOGITS
     dans
    1.03
     people
    0.97
     држа
    0.95
     At
    0.95
     trong
    0.92
     long
    0.88
     wzglę
    0.88
     estoy
    0.86
     revolucion
    0.84
    内心
    0.84
    Activations Density 0.055%

    No Known Activations