© 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. 159783
    Prev
    Next
    INDEX
    Explanations

    Cup slal, traditional bank, your calendar

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

    analysis of processes

    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
    ad
    0.42
    0.42
     =
    0.41
     cod
    0.41
    ++
    0.40
    જુ
    0.40
     God
    0.40
     Universidad
    0.38
     Protestant
    0.38
     at
    0.38
    POSITIVE LOGITS
     중요한
    0.54
     ዲ
    0.52
    "،
    0.51
     ہیں۔
    0.51
     테이블
    0.50
     нужны
    0.49
     табли
    0.49
     प्रिंट
    0.49
    疣
    0.49
     紙
    0.48
    Activations Density 0.001%

    No Known Activations