© 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-65K
    4. 5004
    Prev
    Next
    INDEX
    Explanations

    percentages and quantities

    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_65k_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
     Inclusive
    0.71
     Porque
    0.69
     Level
    0.69
     નજી
    0.67
     Otherwise
    0.66
    ኀ
    0.66
    ূর্ন
    0.66
    攏
    0.64
    色々
    0.64
     Excess
    0.64
    POSITIVE LOGITS
     out
    1.13
     thirds
    0.91
     percent
    0.86
    out
    0.82
     outta
    0.81
    outof
    0.78
    percent
    0.76
    thirds
    0.74
     tenths
    0.74
     ति
    0.72
    Activations Density 0.087%

    No Known Activations