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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 4759
    Prev
    Next
    INDEX
    Explanations

    circle cx

    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
    ا
    2.33
    ת
    2.13
    al
    1.88
    특별시
    1.81
    lerine
    1.73
    льним
    1.73
    יות
    1.72
    นี้
    1.69
    lerini
    1.68
    い
    1.66
    POSITIVE LOGITS
    imgs
    1.48
    ène
    1.34
     fluores
    1.30
     उसमें
    1.28
     выска
    1.28
     указыва
    1.25
     tardes
    1.24
     proportionality
    1.23
    ⛄
    1.21
     poni
    1.20
    Activations Density 0.000%

    No Known Activations