© 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. 235813
    Prev
    Next
    INDEX
    Explanations

    works and employees

    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
    บา
    0.47
     laser
    0.46
     size
    0.45
     tha
    0.45
    ประสิทธิภาพ
    0.44
    -
    0.43
    ธ
    0.43
     t
    0.43
    ิญ
    0.42
    moto
    0.42
    POSITIVE LOGITS
     skriver
    0.55
    ڎ
    0.48
     comunidades
    0.47
    呈现
    0.47
     apresentar
    0.46
    呈現
    0.45
     одного
    0.45
    볶
    0.45
    ँग
    0.45
     сказали
    0.44
    Activations Density 0.001%

    No Known Activations