© 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. 178590
    Prev
    Next
    INDEX
    Explanations

    sections, districts, plans, DNA, pictures

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

    list items and comparisons

    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
     როგორ
    0.49
     दिलाया
    0.47
     продовжу
    0.46
     Tomcat
    0.46
     เขียน
    0.46
     ל
    0.44
    র্পণ
    0.44
     стаття
    0.44
     Gear
    0.43
    訫
    0.43
    POSITIVE LOGITS
     acet
    0.51
     oxid
    0.50
    _{+}\
    0.48
     offset
    0.45
     asymmetries
    0.44
    EnumValue
    0.43
    specificity
    0.43
     asymmetry
    0.43
     unfavourable
    0.42
    selectedValue
    0.42
    Activations Density 0.000%

    No Known Activations