© 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-3-270M-IT
    5. 15-GEMMASCOPE-2-RES-262K
    7. 70261
    Prev
    Next
    INDEX
    Explanations

    button clicked

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-it/resid_post/layer_15_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
    s
    1.63
    的
    1.43
    יים
    1.34
    sion
    1.30
    の
    1.28
    的精神
    1.25
    xing
    1.23
    ため
    1.21
    ingan
    1.12
    moji
    1.10
    POSITIVE LOGITS
    aila
    1.71
     hatches
    1.56
     Herd
    1.54
     sikker
    1.54
     massa
    1.52
     splashes
    1.52
     wasps
    1.52
    음
    1.51
     Ото
    1.51
     quần
    1.47
    Activations Density 0.000%

    No Known Activations