© 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-262K
    7. 15089
    Prev
    Next
    INDEX
    Explanations

    imperative verbs followed by specific words

    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_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
    ፀ
    0.77
    няется
    0.75
     unver
    0.72
    ဃ
    0.71
     فولت
    0.70
     zeigt
    0.69
    াচ্ছে
    0.69
     microorgan
    0.69
     इंटेल
    0.68
     autrefois
    0.68
    POSITIVE LOGITS
     Them
    0.98
     them
    0.97
    them
    0.85
    近く
    0.76
    圓
    0.73
    round
    0.71
     your
    0.71
     quarry
    0.68
     round
    0.68
    ೀಲ
    0.66
    Activations Density 0.000%

    No Known Activations