© 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. 221275
    Prev
    Next
    INDEX
    Explanations

    percentages, per cent, 90%, 20.9%, 3.91%, 31.1%, 48%

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

    division and calculation outcomes

    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
     พิ
    0.41
     λε
    0.41
    éseket
    0.40
    টাকে
    0.40
    ธาร
    0.38
     pagare
    0.38
     פי
    0.37
     Zahlung
    0.37
     هال
    0.37
    🐏
    0.37
    POSITIVE LOGITS
     surpr
    0.45
     corr
    0.44
     dict
    0.44
     sorpresa
    0.43
     dictatorship
    0.42
     Dict
    0.40
    ாடு
    0.40
     Corr
    0.40
     correction
    0.39
     against
    0.38
    Activations Density 0.007%

    No Known Activations