© 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-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 35005
    Prev
    Next
    INDEX
    Explanations

    ending or last item

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    inerario
    -1.19
     podat
    -1.09
     ulica
    -1.08
    liceerd
    -1.07
     zato
    -1.05
    ᠮ
    -1.05
    他已经
    -1.03
     lámparas
    -1.03
    ---|---|
    -1.03
    istungen
    -1.03
    POSITIVE LOGITS
    I
    1.18
    Lastly
    1.18
    ,
    1.12
     Lastly
    1.11
     are
    1.09
     final
    1.05
     finally
    1.05
    N
    1.02
    。　　
    0.98
    蜿
    0.98
    Activations Density 0.008%

    No Known Activations