© 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. 185254
    Prev
    Next
    INDEX
    Explanations

    illustrates a

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

    ensure fertility and good fortune

    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
     Soren
    0.47
     εξε
    0.44
     ATMs
    0.43
     VLC
    0.42
     tRNA
    0.41
    খানার
    0.41
     বিলা
    0.41
    ჩ
    0.41
     الفيديو
    0.41
     حالا
    0.41
    POSITIVE LOGITS
    सामान्यीकृत
    0.52
    <0x80>
    0.50
    неоп
    0.49
    ፈላጊ
    0.47
    uniformly
    0.47
    必須
    0.47
    詬
    0.47
    筠
    0.46
    пробу
    0.45
    َح
    0.45
    Activations Density 0.001%

    No Known Activations