© 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. 31422
    Prev
    Next
    INDEX
    Explanations

    found within

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

    Debate Club, builder, job within

    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
    的网络
    0.48
     โอ
    0.48
     네트워크
    0.46
     Weiß
    0.46
     以
    0.45
    的世界
    0.45
    博物馆
    0.42
    提供的
    0.42
     实
    0.42
     Museu
    0.42
    POSITIVE LOGITS
     pocos
    0.52
     geri
    0.52
    clonal
    0.52
    REEN
    0.51
     quitt
    0.47
    Survived
    0.46
    ーストラ
    0.46
     interfering
    0.46
    chten
    0.45
    inhas
    0.45
    Activations Density 0.000%

    No Known Activations