© 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. 224579
    Prev
    Next
    INDEX
    Explanations

    was happening, blooming from, limited resolution

    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
     зво
    0.42
    湯
    0.41
    同学们
    0.40
     pourquoi
    0.39
     "'
    0.39
    如图
    0.39
     ጡ
    0.38
     Bür
    0.38
    咶
    0.37
     fren
    0.37
    POSITIVE LOGITS
    provides
    0.44
     organizes
    0.41
    Susan
    0.40
    Joe
    0.39
    SUS
    0.38
     organize
    0.37
    bios
    0.37
    CRC
    0.37
    scattering
    0.37
    Verm
    0.36
    Activations Density 0.000%

    No Known Activations