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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-262K
    7. 8412
    Prev
    Next
    INDEX
    Explanations

    tkinter, international

    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
    en
    5.11
    ي
    4.50
    quele
    4.37
    на
    4.32
    로
    4.19
    ed
    3.96
    ა
    3.89
    a
    3.84
    ة
    3.64
    การ
    3.62
    POSITIVE LOGITS
    ক
    3.50
    sin
    2.96
    side
    2.79
    கள்
    2.69
    s
    2.63
    води
    2.63
    skiy
    2.61
    tedy
    2.60
    𝗗
    2.50
    nél
    2.47
    Activations Density 0.077%

    No Known Activations