© 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. 9-GEMMASCOPE-2-RES-262K
    7. 8654
    Prev
    Next
    INDEX
    Explanations

    names of people

    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_9_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
    которые
    1.00
     evitare
    0.97
    ์
    0.97
    =====
    0.91
    Excuse
    0.91
    ==
    0.89
     گے
    0.89
    ت
    0.87
    띈
    0.85
    hasta
    0.85
    POSITIVE LOGITS
     aching
    1.04
     vehemently
    1.01
     queryString
    0.98
     jokes
    0.98
     instincts
    0.98
     paraphr
    0.97
     lungs
    0.96
    łeś
    0.93
    ifier
    0.92
     violently
    0.92
    Activations Density 0.057%

    No Known Activations