© 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. 85101
    Prev
    Next
    INDEX
    Explanations

    who look

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

    work completion, risks, python, structure

    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
    Not in Any Lists

    No Comments

    Negative Logits
     &
    0.50
    ＆
    0.50
    ड
    0.48
     aix
    0.43
     independently
    0.43
     xp
    0.42
     yac
    0.41
     independ
    0.41
     Libertad
    0.41
    ина
    0.40
    POSITIVE LOGITS
     প্রস্তুতি
    0.45
    るので
    0.44
    ตำบล
    0.44
     pretrial
    0.43
    ਲੇ
    0.42
    ⏭
    0.42
    didn
    0.42
    劑
    0.42
    compliant
    0.42
     धरो
    0.42
    Activations Density 0.002%

    No Known Activations