© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 150154
    Prev
    Next
    INDEX
    Explanations

    transportation and locations

    np_acts-logits-general · gemini-2.5-flash-lite

    international language words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <td>
    0.49
    {
    0.47
     proceeded
    0.45
     well
    0.43
     character
    0.43
    <-
    0.42
    hold
    0.42
     bevor
    0.41
     ;
    0.41
     !=
    0.41
    POSITIVE LOGITS
    车站
    0.56
    公交
    0.54
    स्टैंड
    0.53
    蓝牙
    0.53
     교통
    0.53
     पार्किंग
    0.53
     llegada
    0.52
     শিশু
    0.52
     автобу
    0.50
     wheelchairs
    0.50
    Activations Density 0.000%

    No Known Activations