© 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. 185187
    Prev
    Next
    INDEX
    Explanations

    verbs and subsequent words

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

    challenges, opportunities, details

    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
     घेतला
    0.48
    cL
    0.45
    帙
    0.43
     そして
    0.43
     ব্যাবস্থা
    0.42
    筫
    0.42
    ARAJYA
    0.42
    玑
    0.42
    ("--
    0.41
    トム
    0.41
    POSITIVE LOGITS
     Component
    0.47
    ö
    0.45
    ą
    0.44
     VGA
    0.44
     Pint
    0.44
     sibling
    0.43
    在于
    0.43
    mj
    0.43
     Gunnar
    0.43
     Electrode
    0.43
    Activations Density 0.000%

    No Known Activations