© 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. 188125
    Prev
    Next
    INDEX
    Explanations

    autonom, network, music, system

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

    constructing sequences from lineage

    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
     sometimes
    0.46
     A
    0.44
     You
    0.42
    arium
    0.40
    大多
    0.40
     Rhe
    0.40
    tries
    0.40
     kadang
    0.40
     juga
    0.40
    ấ
    0.39
    POSITIVE LOGITS
     автоном
    0.55
     네트워크
    0.48
     শরণার্থীরা
    0.48
    贯
    0.48
    ミュージック
    0.47
     autonome
    0.46
     музыки
    0.45
     システム
    0.45
     শরণার্থীদের
    0.44
     시스템
    0.44
    Activations Density 0.001%

    No Known Activations