© 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. 9308
    Prev
    Next
    INDEX
    Explanations

    class definition

    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
     불구하고
    3.55
    ような
    3.02
     사항
    2.92
    ས་
    2.87
    ئیں
    2.81
    к
    2.70
    parsed
    2.70
     Commandments
    2.61
    ction
    2.59
    ле
    2.55
    POSITIVE LOGITS
    别的
    4.42
    mates
    3.32
    sing
    3.17
    PathResource
    3.04
    forName
    3.03
    _="
    3.01
    sb
    3.01
    enf
    2.90
    מע
    2.85
    sit
    2.79
    Activations Density 0.101%

    No Known Activations