© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 1378
    Prev
    Next
    INDEX
    Explanations

    Indigenous peoples' use of trapping

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_16_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     με
    0.60
    ife
    0.52
     ν
    0.50
    ᱗
    0.49
     ((
    0.49
     archetype
    0.48
    psi
    0.48
    arguments
    0.47
     واقعی
    0.47
    τες
    0.45
    POSITIVE LOGITS
     Jó
    0.52
     Sağ
    0.48
     Gastroenter
    0.48
     Gems
    0.47
     Sparkling
    0.47
     Éd
    0.47
     Sagar
    0.47
     Dokl
    0.47
    ᄐ
    0.47
     पढ़ाई
    0.46
    Activations Density 0.000%

    No Known Activations