© 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. 225430
    Prev
    Next
    INDEX
    Explanations

    processed products

    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
    Nuclear
    0.48
     핵
    0.47
     힘
    0.45
    рах
    0.44
    nuclear
    0.44
     nuclear
    0.43
     기타
    0.43
     mitosis
    0.42
    늬
    0.42
    핵
    0.42
    POSITIVE LOGITS
     édition
    0.54
     Associate
    0.51
     groupes
    0.50
     Associates
    0.49
     groupe
    0.49
    বায়
    0.48
     appealed
    0.48
    कारक
    0.48
     overtook
    0.48
     অবস্থায়
    0.48
    Activations Density 0.002%

    No Known Activations