© 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. 63533
    Prev
    Next
    INDEX
    Explanations

    residential movers

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

    context aware navigation system

    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
    Negative Logits
    ва
    0.50
    {
    0.50
    ї
    0.50
    мат
    0.49
    êu
    0.47
    די
    0.47
    اعت
    0.46
    핑크
    0.45
    ዉ
    0.45
    ወ
    0.44
    POSITIVE LOGITS
    setlength
    0.53
     သိ
    0.49
     foliis
    0.49
    bitflag
    0.48
     આનંદ
    0.48
     desloc
    0.47
     پخش
    0.46
     setor
    0.45
     conquering
    0.45
     cannabinoids
    0.45
    Activations Density 0.001%

    No Known Activations