© 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. 8737
    Prev
    Next
    INDEX
    Explanations

    filepath construction

    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
     oppressed
    1.73
    ع
    1.64
    ifical
    1.60
    Jeśli
    1.57
    د
    1.53
    பார
    1.53
    ت
    1.53
    ▫
    1.48
     толькі
    1.48
    =-\
    1.48
    POSITIVE LOGITS
    បន្ថ
    1.56
    scrape
    1.52
    Ĭ
    1.51
    בין
    1.51
    lanan
    1.46
     floc
    1.45
    Дан
    1.43
     человеком
    1.43
     saga
    1.42
     purpos
    1.41
    Activations Density 0.078%

    No Known Activations