© 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. 246755
    Prev
    Next
    INDEX
    Explanations

    contracts and 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
     Д
    0.54
     defecto
    0.48
     graphique
    0.48
     asimismo
    0.47
    бин
    0.46
     igualmente
    0.46
     Константи
    0.46
    рек
    0.46
    бед
    0.46
    ۔
    0.46
    POSITIVE LOGITS
    to
    0.49
    nl
    0.47
     at
    0.47
     on
    0.46
    South
    0.44
     Mfg
    0.44
    కరించ
    0.43
    amaran
    0.43
     Sixty
    0.41
     Pollution
    0.41
    Activations Density 0.000%

    No Known Activations