© 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. 12-GEMMASCOPE-2-RES-65K
    7. 12
    Prev
    Next
    INDEX
    Explanations

    Excel from rounding

    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_12_width_65k_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
    的
    3.51
    ي
    3.10
    a
    3.04
    y
    3.00
    i
    2.91
    י
    2.88
    ing
    2.87
    es
    2.84
    er
    2.80
    ن
    2.68
    POSITIVE LOGITS
    msk
    2.13
    wb
    1.92
    abbing
    1.92
    px
    1.87
    apis
    1.81
    endaft
    1.81
    tf
    1.80
    7
    1.78
    ixel
    1.77
    dfs
    1.75
    Activations Density 0.243%

    No Known Activations