© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 60329
    Prev
    Next
    INDEX
    Explanations

    trash, rubbish, and pollution

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

    specific words or phrases

    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
    Ằ
    0.46
     محمد
    0.45
     Kurds
    0.43
     Arabs
    0.43
     Protestants
    0.43
    শাহ
    0.42
     жа
    0.42
     முதலில்
    0.41
     کرتی
    0.41
     ग्रीन
    0.40
    POSITIVE LOGITS
    理事
    0.50
    ciem
    0.50
    adika
    0.50
    hong
    0.50
     hyperbol
    0.49
    集
    0.48
    liang
    0.47
    pe
    0.47
    ka
    0.47
    oph
    0.47
    Activations Density 0.000%

    No Known Activations