Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-12B-IT
    3. 12-GEMMASCOPE-2-RES-262K
    4. 577
    Prev
    Next
    INDEX
    Explanations

    interference pattern

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_12_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
    রা
    1.80
    ية
    1.72
    ،
    1.67
    นี้
    1.65
    들이
    1.60
    ian
    1.59
    Questo
    1.59
    কে
    1.54
     Dieses
    1.53
    ively
    1.52
    POSITIVE LOGITS
    e
    2.66
    ا
    1.98
    eine
    1.84
    or
    1.73
     rectángulo
    1.73
    eip
    1.66
    cX
    1.62
    eep
    1.58
    a
    1.54
    дії
    1.53
    Activations Density 0.015%

    No Known Activations