© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 120448
    Prev
    Next
    INDEX
    Explanations

    smartphones, farms, guaranteeing performance

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bleau
    0.39
    zł
    0.39
     shad
    0.39
    Тех
    0.38
     Occ
    0.38
     Львів
    0.38
    sparse
    0.38
    𝑳
    0.38
     അപ
    0.37
    佯
    0.37
    POSITIVE LOGITS
     taas
    0.43
     jää
    0.40
     construct
    0.38
    ђено
    0.38
    ỗng
    0.37
    طا
    0.36
    (()
    0.35
    理解
    0.35
     zitten
    0.35
     drifted
    0.35
    Activations Density 0.000%

    No Known Activations