© 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. 2804
    Prev
    Next
    INDEX
    Explanations

    hopeful or lucky interjections

    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
     geometric
    0.78
     persuaded
    0.78
    <unused497>
    0.77
     astonished
    0.77
     evocative
    0.77
     prepared
    0.76
     insufficiently
    0.75
     assertion
    0.75
     adhered
    0.74
     mathematical
    0.73
    POSITIVE LOGITS
     Hopefully
    0.93
     "
    0.91
    Hopefully
    0.89
     Luckily
    0.83
    Luckily
    0.81
    0.80
     atualmente
    0.80
     tentunya
    0.79
     đc
    0.78
     *"
    0.76
    Activations Density 0.024%

    No Known Activations