© 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-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 30618
    Prev
    Next
    INDEX
    Explanations

    os.walk function

    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
    ва
    0.69
     monomials
    0.57
     bitmaps
    0.56
    བ
    0.50
    ث
    0.49
    ف
    0.48
    στα
    0.48
     Compounds
    0.47
    ందు
    0.46
    铊
    0.46
    POSITIVE LOGITS
    :
    0.75
    ys
    0.57
     প্রতিটি
    0.57
    ilebilir
    0.54
    irin
    0.54
    atip
    0.53
    instrList
    0.53
     iedere
    0.52
    roits
    0.52
     কার্যক্রম
    0.52
    Activations Density 0.001%

    No Known Activations