© 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-262K
    7. 38126
    Prev
    Next
    INDEX
    Explanations

    china

    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_262k_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
    Fraud
    0.40
     fraudulently
    0.39
    PASS
    0.38
    <u>
    0.38
     fraudulent
    0.38
     Prong
    0.37
     prong
    0.37
    }}]
    0.36
    tune
    0.36
     fpr
    0.36
    POSITIVE LOGITS
     tratado
    0.48
     Translated
    0.46
     treated
    0.44
     behand
    0.43
    䏲
    0.43
    Translated
    0.42
     쓰고
    0.42
    只限
    0.41
     మారి
    0.41
     sensorial
    0.41
    Activations Density 0.001%

    No Known Activations