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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 133981
    Prev
    Next
    INDEX
    Explanations

    can help

    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
     neue
    0.43
    ContextMenu
    0.42
    DataGridView
    0.42
     Zeiten
    0.39
    寮
    0.38
     Preferred
    0.38
     ['(?
    0.38
    ຖື
    0.38
     정의역
    0.38
     obj
    0.37
    POSITIVE LOGITS
     जल्दी
    0.40
    ualan
    0.40
    োক
    0.38
    owaniu
    0.38
    mek
    0.37
    Aq
    0.37
     quelconque
    0.37
    Helping
    0.37
    jdbcType
    0.36
    zad
    0.36
    Activations Density 0.000%

    No Known Activations