© 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. 52269
    Prev
    Next
    INDEX
    Explanations

    whom, them, Group, rule, valentine

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

    "love" signifies, "Brexit" signifies

    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
    ка
    0.59
    homogeneous
    0.49
    ი
    0.49
     აღმასრულებელი
    0.48
    یا
    0.48
     ฟ้า
    0.47
    ིག་
    0.46
     DMC
    0.46
     FPGA
    0.46
     മുഖ്യമ
    0.45
    POSITIVE LOGITS
    ullie
    0.47
    ↵↵
    0.47
    eline
    0.46
    引用
    0.45
    招待
    0.44
     allé
    0.43
    elles
    0.43
     teor
    0.43
    Norton
    0.42
    ert
    0.42
    Activations Density 0.000%

    No Known Activations