© 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. 224462
    Prev
    Next
    INDEX
    Explanations

    outlines and structured lists like "I."

    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
    亩
    0.42
     housewife
    0.42
    ༢
    0.42
     ڈ
    0.40
     kader
    0.40
    ക്കണം
    0.40
    市長
    0.39
    axia
    0.39
     آ
    0.39
    ⑫
    0.38
    POSITIVE LOGITS
    pointers
    0.38
     Вулкан
    0.36
     tems
    0.36
     вопросы
    0.36
     Application
    0.36
     concess
    0.36
    contrar
    0.35
    lion
    0.35
     customary
    0.34
     Cusco
    0.34
    Activations Density 0.000%

    No Known Activations