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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 25953
    Prev
    Next
    INDEX
    Explanations

    a new or complete set

    np_acts-logits-general · gemini-2.5-flash-lite

    describing types of outcomes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     통해
    0.70
    ต้อง
    0.62
     तलैया
    0.56
    ได้รับ
    0.51
     を
    0.49
    พัฒนา
    0.49
     iteratively
    0.48
    ത്തിലൂടെ
    0.47
     も
    0.47
     машиналарын
    0.47
    POSITIVE LOGITS
    全新的
    0.64
    新的
    0.58
    完整的
    0.53
    著名的
    0.52
    良好的
    0.52
    什么样的
    0.52
    一系列
    0.51
    特殊的
    0.51
    最佳
    0.50
    类似
    0.50
    Activations Density 0.006%

    No Known Activations