© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 82674
    Prev
    Next
    INDEX
    Explanations

    related specifications or quantities

    np_acts-logits-general · gemini-2.5-flash-lite

    token limits

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     felon
    0.48
     neue
    0.46
     DeFi
    0.46
     feud
    0.46
     bakt
    0.45
    ضافة
    0.45
     SWOT
    0.45
     f
    0.45
     Fetch
    0.45
     milj
    0.44
    POSITIVE LOGITS
     exacta
    0.46
     मुलाकात
    0.44
     constitute
    0.44
     pabbaj
    0.44
     attham
    0.43
     concreta
    0.41
    จริงๆ
    0.41
     concisely
    0.41
     estética
    0.41
     زیبایی
    0.41
    Activations Density 0.002%

    No Known Activations