© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 63558
    Prev
    Next
    INDEX
    Explanations

    contract, tort, express, oral, intentional

    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
    .}$
    0.40
     ক্ষতির
    0.40
    ⌄
    0.40
    ংস
    0.40
    อาจ
    0.40
    ที่จะ
    0.40
     waitFor
    0.39
     شما
    0.39
    ۔
    0.39
     که
    0.38
    POSITIVE LOGITS
     доб
    0.37
    बताया
    0.35
     svým
    0.35
     autocratic
    0.34
     décidé
    0.33
     metodi
    0.33
     rebellion
    0.33
     sociali
    0.33
     hed
    0.33
     passar
    0.33
    Activations Density 0.002%

    No Known Activations