© 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. 226809
    Prev
    Next
    INDEX
    Explanations

    specific nouns followed by detail

    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
    ęcie
    0.53
     بالکل
    0.49
    attuale
    0.49
    нера
    0.47
    現在の
    0.47
    ęła
    0.46
    🔚
    0.46
    が無い
    0.45
    ті
    0.44
    重建
    0.44
    POSITIVE LOGITS
     Feng
    0.41
     Ding
    0.41
    ps
    0.38
     Carry
    0.38
     Chong
    0.38
    <sup>
    0.37
    ist
    0.37
    pruch
    0.37
     {
    0.36
     Rob
    0.36
    Activations Density 0.000%

    No Known Activations