© 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. 40-GEMMASCOPE-2-RES-16K
    7. 11105
    Prev
    Next
    INDEX
    Explanations

    relationships and connections

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

    discovering connections

    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_40_width_16k_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
    同士
    0.59
    与其他
    0.58
     उनसे
    0.53
    与其
    0.51
    与
    0.47
     आपसे
    0.46
     तुमसे
    0.45
     हमसे
    0.44
    と
    0.43
    กับ
    0.43
    POSITIVE LOGITS
     relationship
    0.86
    relationship
    0.80
     관계
    0.78
     ilişk
    0.77
    關係
    0.75
    comparison
    0.73
    の関係
    0.73
     combo
    0.72
     bağlant
    0.71
     соотно
    0.71
    Activations Density 0.205%

    No Known Activations