© 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. 22-GEMMASCOPE-2-RES-262K
    7. 12635
    Prev
    Next
    INDEX
    Explanations

    1880s historical dates

    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_22_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
    ған
    0.93
     réfrig
    0.91
     серьез
    0.88
    ột
    0.88
     commencé
    0.84
    𝚜
    0.84
     monoclonal
    0.83
    ˏ
    0.83
     Camacho
    0.83
    бири
    0.82
    POSITIVE LOGITS
    keeper
    0.86
     colony
    0.79
    rocket
    0.79
     अंग्रेजों
    0.77
    禺
    0.76
    െ
    0.76
    Tre
    0.75
    Fetcher
    0.75
    ${
    0.74
     Php
    0.74
    Activations Density 0.008%

    No Known Activations