© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 61851
    Prev
    Next
    INDEX
    Explanations

    feature learning

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    。
    0.49
    ।
    0.46
     piles
    0.43
     Maui
    0.42
    fires
    0.42
    রা
    0.42
    ে
    0.42
    बार
    0.41
    偷
    0.41
    বন্ধ
    0.40
    POSITIVE LOGITS
     Вол
    0.54
     измерения
    0.50
     sichtbar
    0.49
     став
    0.49
     Совет
    0.48
     є
    0.47
     وح
    0.47
     зберіга
    0.47
     давление
    0.46
     могу
    0.46
    Activations Density 0.002%

    No Known Activations