© 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. 72718
    Prev
    Next
    INDEX
    Explanations

    indefinite articles before nouns

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

    restricting access, powering temporary, free to, pair people

    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
    If
    0.43
     فع
    0.43
    Якщо
    0.41
    م
    0.40
    nodes
    0.40
     Якщо
    0.40
     کودک
    0.39
    Wo
    0.39
     you
    0.39
    чних
    0.38
    POSITIVE LOGITS
    ELEASE
    0.50
     cuba
    0.49
    慰
    0.48
    VSLU
    0.48
    velyan
    0.47
    ამაშ
    0.46
    arlık
    0.46
     क्रांतिकार
    0.46
     keySchedule
    0.46
     komen
    0.45
    Activations Density 0.004%

    No Known Activations