© 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. 111174
    Prev
    Next
    INDEX
    Explanations

    Classification, dangers, tons

    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
    WithFieldContext
    0.39
    QUrl
    0.38
    平衡
    0.38
    双手
    0.38
     QApplication
    0.38
    调度
    0.38
     derivada
    0.38
    湡
    0.38
    <unused44>
    0.37
    输出
    0.37
    POSITIVE LOGITS
     fan
    0.51
     Mol
    0.43
     nearby
    0.41
    분
    0.40
     mol
    0.40
    াপ্র
    0.40
     individuals
    0.39
     spray
    0.39
     kong
    0.39
    팬
    0.39
    Activations Density 0.000%

    No Known Activations