© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 9838
    Prev
    Next
    INDEX
    Explanations

    reliability

    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
    с
    3.89
    ї
    3.72
    ें
    3.71
    ن
    3.70
    quoi
    3.59
    ها
    3.58
    𝚖
    3.57
    𝚍
    3.54
    𝚘
    3.40
    𝚢
    3.37
    POSITIVE LOGITS
    tion
    4.50
    ात
    4.30
    o
    4.11
    이
    4.09
    t
    3.95
    tions
    3.87
    tional
    3.79
    tie
    3.74
    т
    3.73
    tak
    3.65
    Activations Density 0.057%

    No Known Activations