© 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. 9048
    Prev
    Next
    INDEX
    Explanations

    keys and values

    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
    𝑢
    3.18
    岸
    3.09
    𝑔
    3.07
    𝑂
    3.05
    𝐔
    2.96
    ੍
    2.93
    𝑀
    2.85
    𝑃
    2.82
    𝐴
    2.80
    𝑦
    2.77
    POSITIVE LOGITS
    ed
    4.59
    ת
    4.50
    el
    3.69
    ة
    3.42
    ку
    3.37
    ంచి
    3.31
    et
    3.28
    ing
    3.25
    es
    3.23
    ला
    3.13
    Activations Density 0.019%

    No Known Activations