© 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. 26438
    Prev
    Next
    INDEX
    Explanations

    punctuation and spaces

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

    art scene, museums, contemporary

    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
    发电
    0.44
    Organ
    0.41
    离婚
    0.39
    ​
    0.39
    冠军
    0.39
    莳
    0.39
    定义
    0.38
    稳定
    0.38
    Yam
    0.38
    ]【
    0.38
    POSITIVE LOGITS
    ところが
    0.44
     împre
    0.43
     Accordingly
    0.43
     பெரும்பாலும்
    0.42
     themselves
    0.41
     それぞれ
    0.40
     جي
    0.40
    ict
    0.39
    れの
    0.39
     হচ্ছিল
    0.39
    Activations Density 0.006%

    No Known Activations