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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 10167
    Prev
    Next
    INDEX
    Explanations

    roles and positions

    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
     ਮੁ
    0.42
     আকর্ষণ
    0.42
    einander
    0.41
    GUILayout
    0.41
    rapolation
    0.40
     lưng
    0.40
    cić
    0.39
     后
    0.39
    ker
    0.38
     العق
    0.38
    POSITIVE LOGITS
    Do
    0.41
     статьи
    0.41
     ситуации
    0.40
    薗
    0.40
    개
    0.39
     Harrow
    0.38
     MANY
    0.38
     understand
    0.38
    İ
    0.38
    ИН
    0.38
    Activations Density 0.003%

    No Known Activations