© 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. 13170
    Prev
    Next
    INDEX
    Explanations

    invest followed by currency

    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
    最多的
    0.52
    的
    0.50
    出来的
    0.45
    家庭
    0.45
    最大的
    0.44
    我在
    0.43
    客户
    0.43
     الو
    0.42
    Debt
    0.42
    出来
    0.42
    POSITIVE LOGITS
     tailles
    0.53
    ק
    0.49
    ח
    0.48
     attaque
    0.48
     entend
    0.47
    িয়াছে
    0.47
     largura
    0.47
     investir
    0.46
     enfrent
    0.45
     sombre
    0.45
    Activations Density 0.002%

    No Known Activations