© 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. 102862
    Prev
    Next
    INDEX
    Explanations

    legal and financial definitions

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

    initial product development

    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
     հատ
    0.43
    ָ
    0.42
    工作人员
    0.40
     צי
    0.40
    ַ
    0.40
     საკ
    0.39
    ﻤ
    0.39
    גר
    0.38
    ახებ
    0.38
    浐
    0.38
    POSITIVE LOGITS
     विद्रोह
    0.46
     securities
    0.44
     persen
    0.44
    turbo
    0.43
     teori
    0.43
    dle
    0.42
     strategi
    0.42
     reinsurance
    0.42
     teorie
    0.42
    afu
    0.42
    Activations Density 0.000%

    No Known Activations