© 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. 16-GEMMASCOPE-2-RES-262K
    7. 2668
    Prev
    Next
    INDEX
    Explanations

    network interface names `wlan*` `eth*`

    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_16_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
     to
    1.32
    s
    1.26
    ,
    1.08
     at
    1.07
    y
    1.05
    ’
    1.05
    ä
    1.03
     that
    1.00
    arg
    0.94
    ing
    0.93
    POSITIVE LOGITS
    ু
    1.02
    em
    0.94
    もら
    0.84
    া
    0.84
    ه
    0.84
    ল
    0.83
    㑹
    0.81
    る
    0.80
    uje
    0.79
    <0x0D>
    0.79
    Activations Density 0.068%

    No Known Activations