© 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. 74771
    Prev
    Next
    INDEX
    Explanations

    after claim or for Golden

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

    ChatGPT and AI models

    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
    k
    0.55
     Information
    0.54
     Due
    0.52
     INFORMATION
    0.50
     Ми
    0.49
    েন্টস
    0.49
     Baill
    0.49
     with
    0.47
     В
    0.47
    ל
    0.47
    POSITIVE LOGITS
     rendszer
    0.49
     hatal
    0.47
     infecciones
    0.46
     enfermedades
    0.46
    Bibli
    0.45
     系统
    0.44
    难题
    0.44
     trastornos
    0.43
     заболевания
    0.43
     conjuntos
    0.43
    Activations Density 0.000%

    No Known Activations