© 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. 23961
    Prev
    Next
    INDEX
    Explanations

    words following certain phrases

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

    display, necklace, services

    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
     neighbouring
    0.56
     podían
    0.48
     their
    0.47
     selepas
    0.46
     durante
    0.44
     Š
    0.44
     specialised
    0.43
     diejenigen
    0.43
     Neighbour
    0.42
     Schle
    0.42
    POSITIVE LOGITS
    发生在
    0.48
    打印
    0.48
    干净
    0.48
    软件包
    0.47
    程序
    0.47
    习惯
    0.46
    物联网
    0.46
    羟
    0.46
    蚝
    0.46
    出门
    0.46
    Activations Density 0.000%

    No Known Activations