© 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. 9260
    Prev
    Next
    INDEX
    Explanations

    shredded or grated food

    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
    𝑘
    2.85
    ки
    2.81
    ᵗ
    2.70
    べき
    2.63
    सीय
    2.59
    an
    2.49
    w
    2.42
    اد
    2.38
     plurality
    2.38
     kilobytes
    2.32
    POSITIVE LOGITS
    м
    2.84
    ım
    2.70
    #######
    2.60
     vilka
    2.46
    вості
    2.44
    ท์
    2.36
    ต้อง
    2.23
    علي
    2.20
     cuentas
    2.20
    aia
    2.18
    Activations Density 0.034%

    No Known Activations