© 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. 4340
    Prev
    Next
    INDEX
    Explanations

    movement to locations

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

    movement to a location

    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
     Wanneer
    0.17
    设置为
    0.16
     Cuando
    0.14
    按钮
    0.14
     файлы
    0.14
    攵
    0.14
    các
    0.14
    圆形
    0.14
    強制
    0.14
    Cuando
    0.14
    POSITIVE LOGITS
     there
    0.21
     someplace
    0.21
     allí
    0.20
     afield
    0.20
     acolo
    0.19
     elsewhere
    0.19
     সেখানে
    0.18
     abroad
    0.17
     곳
    0.17
     outdoors
    0.17
    Activations Density 0.748%

    No Known Activations