Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-1B-IT
    3. 17-GEMMASCOPE-2-RES-16K
    4. 28
    Prev
    Next
    INDEX
    Explanations

    subject followed by past tense verb

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_17_width_16k_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
     කරයි
    1.15
     mohou
    1.08
     وي
    1.05
     वाटते
    1.01
     দিচ্ছেন
    1.00
     کوي
    0.99
    вает
    0.97
     وير
    0.97
     নিচ্ছে
    0.96
     ہیں
    0.95
    POSITIVE LOGITS
     was
    3.61
    was
    2.92
     were
    2.88
     wasn
    2.87
     didn
    2.73
     did
    2.70
     had
    2.68
     became
    2.59
    Was
    2.58
     took
    2.55
    Activations Density 2.137%

    No Known Activations