© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 6993
    Prev
    Next
    INDEX
    Explanations

    tarzan and tarpaulin

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

    tar, tarps, tariffs

    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
    泰
    0.41
    läss
    0.39
     हस्त
    0.39
    Рис
    0.38
    ська
    0.38
    姫
    0.38
     Solutions
    0.37
    떻
    0.37
    டிய
    0.37
    仪表
    0.36
    POSITIVE LOGITS
     tar
    0.97
     Tar
    0.84
    Tar
    0.82
    tar
    0.80
     TAR
    0.63
     tariffs
    0.58
     tariff
    0.57
    TAR
    0.56
     tarp
    0.55
    tariff
    0.52
    Activations Density 0.004%

    No Known Activations