© 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. 813
    Prev
    Next
    INDEX
    Explanations

    contrasting conjunctions and their disclaimers

    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
    াল
    0.57
    и
    0.56
    ح
    0.52
    а
    0.50
    ️
    0.50
    С
    0.49
    щения
    0.49
    े
    0.48
    های
    0.48
    and
    0.48
    POSITIVE LOGITS
     alas
    0.85
    termilk
    0.80
     hey
    0.77
     they
    0.69
     it
    0.68
     nevertheless
    0.67
    thole
    0.67
     crucially
    0.67
     unfortunately
    0.67
     nonetheless
    0.66
    Activations Density 0.146%

    No Known Activations