© 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. 88958
    Prev
    Next
    INDEX
    Explanations

    number of bedrooms

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

    file upload

    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
    ‶
    0.46
    岳
    0.45
    広く
    0.45
    িপুর
    0.45
     நிர்வாக
    0.43
    ≲
    0.42
    のス
    0.42
    や
    0.42
     находится
    0.41
    ◅
    0.41
    POSITIVE LOGITS
     BUREAU
    0.43
    ORMAL
    0.41
    icy
    0.41
    DataFrame
    0.41
    клады
    0.41
    全部
    0.40
     якія
    0.40
    Argument
    0.39
     bureau
    0.39
    fY
    0.38
    Activations Density 0.001%

    No Known Activations