© 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. 29386
    Prev
    Next
    INDEX
    Explanations

    segregation Soviet jail

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

    specific entities and components

    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
     নদীর
    0.54
    
    0.52
    每個
    0.50
    鵝
    0.46
    0.46
    圖片
    0.46
    ᾧ
    0.44
    𝜌
    0.44
    ἆ
    0.43
    🫧
    0.43
    POSITIVE LOGITS
     segregation
    0.47
     segregated
    0.46
     พวก
    0.45
     porque
    0.44
     Soviet
    0.44
     jail
    0.44
     debunk
    0.43
     เพราะ
    0.43
     segreg
    0.43
     AMC
    0.42
    Activations Density 0.000%

    No Known Activations