© 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. 55689
    Prev
    Next
    INDEX
    Explanations

    of companies

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

    risk and retention

    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
    ał
    0.48
     როგორ
    0.46
     მაგრამ
    0.46
    윳
    0.44
    ̣i
    0.42
     Анаста
    0.42
     খেলা
    0.42
    ÜR
    0.42
    əri
    0.42
     debt
    0.41
    POSITIVE LOGITS
    ك
    0.50
    يد
    0.48
    MTV
    0.48
    د
    0.46
    طل
    0.45
     Farming
    0.44
    シル
    0.44
    جه
    0.44
    لها
    0.44
    ول
    0.43
    Activations Density 0.001%

    No Known Activations