© 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. 90643
    Prev
    Next
    INDEX
    Explanations

    academic or event context

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

    farming

    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
    ía
    0.54
    corto
    0.54
    😳
    0.52
    currentUser
    0.51
     Putri
    0.49
     espes
    0.48
    beh
    0.47
     パンツ
    0.47
    ฿
    0.47
    blusas
    0.46
    POSITIVE LOGITS
     farmed
    0.45
    farming
    0.43
    ULTURAL
    0.43
    रेस्ट
    0.42
     MUST
    0.42
     MAKING
    0.42
    必须
    0.41
    Agricultural
    0.41
     doivent
    0.41
    лектро
    0.41
    Activations Density 0.000%

    No Known Activations