© 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. 80988
    Prev
    Next
    INDEX
    Explanations

    describing concepts and actions

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

    insurance policy

    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
    其次
    0.47
    دن
    0.44
    幼稚
    0.44
     Producers
    0.43
    其中包括
    0.43
    脂肪
    0.42
    的国家
    0.42
    稚
    0.42
    涉及
    0.42
    襁
    0.41
    POSITIVE LOGITS
     шли
    0.51
     обеспечи
    0.50
     операций
    0.50
    से
    0.49
    षक
    0.49
     automate
    0.49
     эффектив
    0.48
     whenever
    0.48
     passable
    0.48
    া
    0.48
    Activations Density 0.000%

    No Known Activations