© 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. 99407
    Prev
    Next
    INDEX
    Explanations

    for income

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

    sample percentage

    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
    सबसे
    0.50
    경제
    0.49
    Само
    0.49
     समझा
    0.48
    С
    0.47
    Пре
    0.47
    㓞
    0.46
    твор
    0.46
    backend
    0.46
    现在
    0.46
    POSITIVE LOGITS
     inhomogeneities
    0.52
     Hm
    0.49
     車
    0.48
     对象
    0.47
     gb
    0.45
     動物
    0.45
     herring
    0.43
     oi
    0.43
     彼
    0.42
     Hp
    0.42
    Activations Density 0.002%

    No Known Activations