© 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. 22970
    Prev
    Next
    INDEX
    Explanations

    mixed reality, current oversight

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

    complex and simple concepts

    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
    🎈
    0.48
    waitSeconds
    0.47
    <h4>
    0.46
    <0x9B>
    0.45
    
    0.45
    ElapsedTime
    0.44
    <h3>
    0.44
    ли
    0.44
    기
    0.44
    どんどん
    0.43
    POSITIVE LOGITS
     formada
    0.46
     justru
    0.46
     និង
    0.46
     verband
    0.44
     සහ
    0.44
     ebenfalls
    0.44
    etheless
    0.43
     semej
    0.43
     indeed
    0.43
     anzi
    0.43
    Activations Density 0.000%

    No Known Activations