© 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. 151786
    Prev
    Next
    INDEX
    Explanations

    familiar with contents

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

    mass energy equivalence

    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
     ちょっと
    0.52
    مل
    0.50
     dài
    0.49
     書
    0.48
     coûts
    0.48
    دول
    0.48
     بن
    0.48
     ถึง
    0.47
    লির
    0.47
     halfCanvas
    0.46
    POSITIVE LOGITS
    fabrik
    0.47
    z
    0.46
    ed
    0.45
    zada
    0.45
     sungai
    0.44
    FAQ
    0.44
     reck
    0.44
    ic
    0.43
    FER
    0.43
    ig
    0.43
    Activations Density 0.000%

    No Known Activations