© 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. 106376
    Prev
    Next
    INDEX
    Explanations

    what this/that means

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

    what that means

    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
    はその
    0.51
    したのは
    0.48
    ព័
    0.47
    を行います
    0.47
     gikk
    0.46
    рін
    0.46
    Gosudarstvennyj
    0.46
     muque
    0.45
    进行了
    0.45
    椛
    0.45
    POSITIVE LOGITS
     MEANS
    0.43
     means
    0.41
     fuss
    0.40
     geometrically
    0.40
    means
    0.39
    meaning
    0.39
    l
    0.38
     consist
    0.38
     FCC
    0.38
     meaning
    0.36
    Activations Density 0.069%

    No Known Activations