© 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
    2. Gemma-3-4B-IT
    3. 9-GEMMASCOPE-2-RES-262K
    4. 8665
    Prev
    Next
    INDEX
    Explanations

    football and Shakespeare

    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
     meisten
    2.17
    ला
    1.89
    ため
    1.84
    yı
    1.82
     meeste
    1.76
    ために
    1.74
    zelfde
    1.64
    l
    1.60
     предназна
    1.59
    es
    1.56
    POSITIVE LOGITS
    ية
    1.67
    इसके
    1.60
    Subsequently
    1.57
    ECH
    1.50
    ồ
    1.49
     aden
    1.48
    battle
    1.43
    ডেইলি
    1.43
    उन्होंने
    1.43
    畊
    1.42
    Activations Density 0.023%

    No Known Activations