© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 3839
    Prev
    Next
    INDEX
    Explanations

    cross, crossexamination

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

    cross and crossed words

    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
    藿
    0.38
    鹖
    0.37
    োধন
    0.35
    fhir
    0.35
    ொ
    0.34
    𝒉
    0.33
    Runtime
    0.33
     बैक्टी
    0.33
    
    0.33
    崙
    0.32
    POSITIVE LOGITS
     cross
    4.78
    cross
    4.72
    Cross
    4.69
     CROSS
    4.63
     Cross
    4.59
    CROSS
    4.44
     क्रॉस
    4.25
     crosses
    3.94
    クロス
    3.94
     ক্রস
    3.89
    Activations Density 0.321%

    No Known Activations