© 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. 24086
    Prev
    Next
    INDEX
    Explanations

    end / ending / tail

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

    end or tail

    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
    玤
    0.47
     démarche
    0.43
     bundan
    0.43
     शुरु
    0.43
     सुबह
    0.43
     बुधवार
    0.43
     মাঝে
    0.42
    HTTPRequest
    0.42
     właścic
    0.41
     marad
    0.41
    POSITIVE LOGITS
    尾
    1.04
     末
    0.98
    结尾
    0.96
    末
    0.91
     tail
    0.89
     end
    0.88
     نهاية
    0.82
     akhir
    0.79
    最后的
    0.79
     terminal
    0.76
    Activations Density 0.131%

    No Known Activations