© 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. 235681
    Prev
    Next
    INDEX
    Explanations

    afternoon shoes analysis Saving bass

    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
     ለ
    0.54
     перевоз
    0.52
     efectuar
    0.52
     afectada
    0.52
     conservar
    0.51
     пе
    0.50
     efectu
    0.50
     afectar
    0.50
     блоки
    0.48
     afect
    0.48
    POSITIVE LOGITS
    žen
    0.46
     przyn
    0.43
    モンド
    0.42
    ングル
    0.42
    െല്ലാം
    0.41
    ]
    0.41
    اقات
    0.41
    就會
    0.40
    ത്തും
    0.40
    裝
    0.40
    Activations Density 0.000%

    No Known Activations