© 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. 119802
    Prev
    Next
    INDEX
    Explanations

    forms and themes

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

    listen to music/podcast

    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
    HPV
    0.47
    碰
    0.47
    шает
    0.44
    权利
    0.44
    肠
    0.42
    腭
    0.42
    getFlight
    0.41
     যেহেতু
    0.41
    為了
    0.41
    俩
    0.40
    POSITIVE LOGITS
     entusi
    0.50
     salido
    0.48
     Firms
    0.47
     FSB
    0.46
     IFS
    0.46
     già
    0.46
     austri
    0.45
    дзе
    0.44
     सैकड़ों
    0.44
     Escobar
    0.44
    Activations Density 0.000%

    No Known Activations