© 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. 9507
    Prev
    Next
    INDEX
    Explanations

    technical and biological concepts

    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
    ੀ
    1.74
     chịu
    1.52
    ก
    1.49
    ात
    1.49
    ا
    1.47
    dery
    1.46
     entrusted
    1.44
    en
    1.43
    ים
    1.41
    கி
    1.39
    POSITIVE LOGITS
    𝚖
    1.74
    𝐧
    1.59
    𝐬
    1.57
    𝚞
    1.57
    ें
    1.56
    𝚐
    1.54
    𝚊
    1.54
    য়
    1.54
    𝚍
    1.52
    𝚌
    1.48
    Activations Density 0.122%

    No Known Activations