© 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-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 134326
    Prev
    Next
    INDEX
    Explanations

    chang followed by names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_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
    艰难
    0.42
    Panoramic
    0.41
    ябре
    0.41
    بري
    0.41
    مس
    0.40
    قف
    0.38
    ጪ
    0.38
    эг
    0.38
    نائي
    0.37
    विधि
    0.37
    POSITIVE LOGITS
    )\\
    0.48
    =|
    0.43
     billion
    0.41
    った
    0.40
    raient
    0.40
    cklenburg
    0.39
    START
    0.39
     Citibank
    0.38
    ֱ
    0.38
    drugs
    0.38
    Activations Density 0.003%

    No Known Activations