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-3-4B-IT
    3. 29-GEMMASCOPE-2-RES-262K
    4. 52986
    Prev
    Next
    INDEX
    Explanations

    percent and percentile

    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
    Classical
    1.11
    ﻯ
    1.06
    classical
    1.06
     التى
    1.03
    انى
    1.02
    ى
    1.01
     बिज़नेस
    0.99
     classical
    0.97
    ∆
    0.94
    نى
    0.94
    POSITIVE LOGITS
     percent
    2.80
    percent
    2.59
    Percent
    2.45
     Percent
    2.43
     percents
    1.95
     PERCENT
    1.77
     Prozent
    1.74
    PERCENT
    1.72
     percentile
    1.49
     persen
    1.39
    Activations Density 0.017%

    No Known Activations