© 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. 48912
    Prev
    Next
    INDEX
    Explanations

    on Friday

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

    medical, legal, and descriptive phrases

    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
    द्रता
    0.50
     آورد
    0.48
    ”，
    0.47
    代引
    0.47
     熱
    0.46
    separatedBy
    0.45
     શુભ
    0.45
    化合物
    0.45
    级别
    0.45
     воздух
    0.44
    POSITIVE LOGITS
    ಾಗ
    0.45
     Ngf
    0.45
    ໆ
    0.44
     bn
    0.43
    же
    0.42
    வே
    0.42
    मौ
    0.42
     хоть
    0.42
    ƣ
    0.41
    ՛
    0.41
    Activations Density 0.000%

    No Known Activations