© 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. 98369
    Prev
    Next
    INDEX
    Explanations

    negative emotions, locations, descriptions, abstract concepts

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

    event details and legacy

    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
     एडिटिंग
    0.51
    capability
    0.48
    準
    0.48
    दर्शिता
    0.48
    isan
    0.47
    hle
    0.47
    ainless
    0.46
    putting
    0.46
    ampuan
    0.45
     эффективность
    0.45
    POSITIVE LOGITS
    的声音
    0.53
    的应用
    0.49
    怎么样
    0.45
    通
    0.45
    తి
    0.45
    实的
    0.44
    র
    0.44
    实
    0.43
     institutions
    0.42
    :|
    0.42
    Activations Density 0.000%

    No Known Activations