© 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. 10311
    Prev
    Next
    INDEX
    Explanations

    chances of

    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
    𝘀
    3.23
    𝗮
    3.15
     magnetores
    3.12
    𝗵
    3.07
    heme
    2.93
    𝘆
    2.92
    𝗽
    2.88
    𝗹
    2.81
    𝗰
    2.77
    𝗲
    2.73
    POSITIVE LOGITS
    mals
    2.93
    ن
    2.69
    𝐫
    2.58
    न
    2.57
    beeld
    2.54
    ক
    2.53
    κα
    2.49
    ва
    2.45
     त्यस
    2.43
    ট
    2.42
    Activations Density 0.019%

    No Known Activations