© 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
    2. Gemma-3-4B-IT
    3. 29-GEMMASCOPE-2-RES-262K
    4. 148846
    Prev
    Next
    INDEX
    Explanations

    answer questions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_29_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
     tensors
    1.04
     dermatitis
    0.97
    녘
    0.92
     ስርዓ
    0.91
     ஆதார
    0.90
     colch
    0.89
     অক্ষরে
    0.87
    akkhand
    0.86
     dignidad
    0.84
     Tensor
    0.83
    POSITIVE LOGITS
    And
    0.82
    Last
    0.77
    Negoti
    0.74
     Walpole
    0.74
    Base
    0.73
     cetera
    0.73
    ('/').
    0.73
    需要在
    0.71
    uc
    0.70
    Into
    0.70
    Activations Density 0.001%

    No Known Activations