© 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. 75087
    Prev
    Next
    INDEX
    Explanations

    French real estate terms

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

    historical roots and BCE dates

    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
    عمل
    0.49
    صرية
    0.44
    뿜
    0.44
    жив
    0.43
    결
    0.43
    жить
    0.43
    剖
    0.43
    номи
    0.42
    ルーム
    0.41
    묘
    0.41
    POSITIVE LOGITS
    om
    0.54
    er
    0.51
    ocèle
    0.50
    orno
    0.50
    ick
    0.49
    erne
    0.49
     warrant
    0.49
    erry
    0.49
    ení
    0.49
    erin
    0.49
    Activations Density 0.000%

    No Known Activations