© 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. 238922
    Prev
    Next
    INDEX
    Explanations

    philanthropy, removed

    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
    raf
    0.49
    }>
    0.49
    ug
    0.47
     ту
    0.46
     >
    0.46
    iper
    0.45
     atu
    0.45
     अर्ध
    0.45
    ipp
    0.45
    iber
    0.45
    POSITIVE LOGITS
    지
    0.50
    лость
    0.50
    지와
    0.49
    פט
    0.48
    ⚉
    0.47
    ソフトウェア
    0.47
    라
    0.46
    министра
    0.46
    模型
    0.45
    ला
    0.44
    Activations Density 0.000%

    No Known Activations