© 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-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 13252
    Prev
    Next
    INDEX
    Explanations

    mathematical formula endings

    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
     letto
    -1.10
    HttpStatusCode
    -1.09
    ：……
    -1.09
     قبل
    -1.09
     senhora
    -1.09
     Rússia
    -1.05
     существу
    -1.05
     intptr
    -1.05
    🦣
    -1.02
     У
    -1.01
    POSITIVE LOGITS
     nephe
    1.07
    Comté
    1.05
     betalen
    1.02
     signaler
    1.02
     crat
    1.01
    就可以了
    1.01
     voelen
    1.01
    телями
    1.00
     and
    0.97
     Ghi
    0.96
    Activations Density 0.002%

    No Known Activations