© 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. 102838
    Prev
    Next
    INDEX
    Explanations

    processing personal data or objectiondirect injectioncompanies bypresented at

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

    lists of names or terms

    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
    k
    0.51
     usher
    0.49
    nuevo
    0.47
    s
    0.46
    g
    0.44
    x
    0.44
     weakness
    0.44
    i
    0.44
    nd
    0.43
     restructure
    0.43
    POSITIVE LOGITS
     ප
    0.50
    ഷ്ട്ര
    0.50
    তামূলক
    0.48
     සෑම
    0.47
    🔞
    0.46
    矇
    0.46
     संवाद
    0.45
    pinimg
    0.45
     Contact
    0.45
     Fourteenth
    0.44
    Activations Density 0.001%

    No Known Activations