© 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. 119771
    Prev
    Next
    INDEX
    Explanations

    market exchanges

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

    specific context markers

    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
     splash
    0.51
     多く
    0.47
     แบบ
    0.46
     lookout
    0.46
    .
    0.46
     fatten
    0.44
     in
    0.44
     celebratory
    0.44
     activities
    0.43
    กิจกรรม
    0.43
    POSITIVE LOGITS
    WarningLevel
    0.48
    শিকান্ত
    0.47
     eröff
    0.47
    وف
    0.44
    淈
    0.43
    عة
    0.43
    цию
    0.42
     мобиль
    0.42
    ोरेशन
    0.41
    ляция
    0.40
    Activations Density 0.000%

    No Known Activations