© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 163733
    Prev
    Next
    INDEX
    Explanations

    vs, v, versus, between organizations

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

    legal case names

    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
     robuste
    0.48
    퇴
    0.46
     മണ്ണി
    0.45
     ਉਨ੍ਹਾਂ
    0.44
     اﻻ
    0.43
    밋
    0.43
     વિના
    0.42
     pavimento
    0.42
     ความ
    0.42
     repas
    0.42
    POSITIVE LOGITS
     vs
    0.64
     v
    0.60
     बनाम
    0.54
     versus
    0.49
     বিপক্ষে
    0.47
    vs
    0.46
    নাম
    0.41
    versus
    0.41
     przeciw
    0.41
     et
    0.40
    Activations Density 0.070%

    No Known Activations