© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 111844
    Prev
    Next
    INDEX
    Explanations

    Programmable Logic Controllers

    np_acts-logits-general · gemini-2.5-flash-lite

    performance and safety descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     &/
    0.52
    中有
    0.51
    이었
    0.45
    廣
    0.43
    及其
    0.41
     broad
    0.40
    자치
    0.40
    이었다
    0.40
    志
    0.39
    料理
    0.39
    POSITIVE LOGITS
     आर्टिफिशियल
    0.53
     ब्लॉ
    0.48
     ആവശ്യമ
    0.47
     Bournemouth
    0.47
     एनालिसिस
    0.47
     अभी
    0.47
    अभी
    0.47
     एक्सपर्ट
    0.46
     protecting
    0.46
     सेमीफाइनल
    0.46
    Activations Density 0.000%

    No Known Activations