© 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. 143338
    Prev
    Next
    INDEX
    Explanations

    Male airport or holiday

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

    adding or placing something

    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
    出发
    0.48
    少数
    0.47
    捌
    0.46
    ジュール
    0.45
     kib
    0.44
    কার
    0.44
    8
    0.43
    查询
    0.43
    럽
    0.42
    దు
    0.42
    POSITIVE LOGITS
     meteen
    0.54
     orden
    0.52
     communic
    0.47
    Humidity
    0.47
     കഴിയ
    0.47
     getan
    0.47
     gemacht
    0.46
     todos
    0.46
     بدون
    0.46
     Aufgabe
    0.46
    Activations Density 0.001%

    No Known Activations