© 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. 188699
    Prev
    Next
    INDEX
    Explanations

    pages, games, we, floor, resistance, native, with

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

    knew things

    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
    の情報
    0.51
    Ē
    0.47
     později
    0.46
    Ẻ
    0.45
    İM
    0.43
    ਵ
    0.43
    Muchas
    0.42
    Evento
    0.42
     信息
    0.41
    Probably
    0.41
    POSITIVE LOGITS
     forks
    0.43
    将
    0.42
     trapping
    0.42
     concurrently
    0.42
     왼쪽
    0.42
     পিতা
    0.40
     allons
    0.40
     demarc
    0.40
     chakra
    0.40
    🏹
    0.40
    Activations Density 0.001%

    No Known Activations