© 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. 53-GEMMASCOPE-2-RES-65K
    7. 7323
    Prev
    Next
    INDEX
    Explanations

    numbers and specific descriptors

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

    Let's use

    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_53_width_65k_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
     करणाऱ्या
    0.37
     《
    0.37
    ুয়ারি
    0.35
     miniatures
    0.35
    ༔
    0.34
     শোভ
    0.34
    ुअल
    0.34
    ждение
    0.33
    ​​
    0.33
     म्हणा
    0.32
    POSITIVE LOGITS
     C
    1.21
     S
    1.12
     Ds
    1.05
     G
    1.04
     E
    1.03
     Q
    1.03
     D
    1.02
     P
    1.02
     L
    1.02
    Ｚ
    1.02
    Activations Density 0.265%

    No Known Activations