© 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. 197694
    Prev
    Next
    INDEX
    Explanations

    accounts, contracts, skin, members

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

    concepts and definitions

    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
    ونا
    0.46
    ة
    0.45
    喤
    0.44
    蝰
    0.44
    的水
    0.44
     地址
    0.44
    专题
    0.43
    等于
    0.43
    _{(\
    0.43
    是为了
    0.43
    POSITIVE LOGITS
    peace
    0.49
     कष्ट
    0.47
    polish
    0.46
     СМИ
    0.46
    am
    0.46
    เพิ่มเติม
    0.46
     lavish
    0.45
    provision
    0.45
     colomb
    0.45
    Somos
    0.44
    Activations Density 0.001%

    No Known Activations