© 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. 14252
    Prev
    Next
    INDEX
    Explanations

    import annotations

    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
    وه
    0.37
     সঙ্গ
    0.36
     sujetos
    0.36
     padassa
    0.36
    uximab
    0.35
    ی
    0.35
     soggetti
    0.35
    cian
    0.35
    Ра
    0.35
    Subject
    0.35
    POSITIVE LOGITS
    ថ្
    0.39
    んば
    0.39
     finan
    0.38
     uniqu
    0.38
    ez
    0.37
     č
    0.37
     style
    0.36
    lemy
    0.36
    zeum
    0.36
    ខ្សែ
    0.36
    Activations Density 0.000%

    No Known Activations