© 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-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 6581
    Prev
    Next
    INDEX
    Explanations

    install / 安装

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_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
     breeds
    0.57
     evaporated
    0.57
     Bakersfield
    0.55
     klein
    0.52
     vyd
    0.52
     ফলা
    0.52
     pocket
    0.51
    }$.)
    0.51
     marais
    0.51
     frying
    0.50
    POSITIVE LOGITS
     installation
    1.99
     install
    1.92
     Installation
    1.92
    Installation
    1.92
    installation
    1.89
    安装
    1.86
     Installing
    1.82
    安裝
    1.80
     설치
    1.79
    Install
    1.78
    Activations Density 0.725%

    No Known Activations