© 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. 207895
    Prev
    Next
    INDEX
    Explanations

    followed by prepositions or conjunctions

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

    security alerts and technical terms

    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
    ForEach
    0.46
    舢
    0.46
     равна
    0.46
    ⟺
    0.43
    гре
    0.43
    除此之外
    0.43
    APs
    0.42
    惴
    0.42
    фри
    0.41
    ্যারি
    0.41
    POSITIVE LOGITS
     Fukuoka
    0.55
    :
    0.52
    duplicates
    0.49
    PERT
    0.48
    äg
    0.47
    canc
    0.46
     Meinung
    0.46
     aiz
    0.46
     Arbeits
    0.46
     Política
    0.45
    Activations Density 0.000%

    No Known Activations