© 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. 599
    Prev
    Next
    INDEX
    Explanations

    holding back or onto

    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
    ία
    1.09
    lə
    1.06
    িক্স
    1.06
    िक
    1.05
    dail
    1.04
     وان
    1.03
    ح
    1.01
    ње
    1.01
    ्यता
    1.01
    carbonyl
    1.00
    POSITIVE LOGITS
     aloft
    2.17
     sway
    2.06
     accountable
    1.94
     hostage
    1.61
     grudge
    1.59
     captive
    1.47
     onto
    1.41
    不住
    1.40
    ครอง
    1.39
    住了
    1.36
    Activations Density 0.071%

    No Known Activations