© 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-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-65K
    7. 5810
    Prev
    Next
    INDEX
    Explanations

    've + past participle or got

    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_22_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
    ка
    1.83
    l
    1.54
    اً
    1.53
    ের
    1.48
    ان
    1.47
    т
    1.37
    ों
    1.37
    os
    1.36
    িক
    1.33
    of
    1.32
    POSITIVE LOGITS
     gotta
    2.45
     got
    2.12
     been
    1.84
    र्गत
    1.56
     Gotta
    1.53
     guna
    1.51
     gotten
    1.48
     Got
    1.48
     Been
    1.48
     alimentaires
    1.46
    Activations Density 0.121%

    No Known Activations