© 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. 10-GEMMASCOPE-RES-131K
    7. 12655
    Prev
    Next
    INDEX
    Explanations

    code work

    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_10/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
    erva
    -1.09
     patrimonio
    -1.03
    还没
    -1.01
     only
    -1.01
     compañ
    -1.01
    ORPG
    -0.99
     GRANDE
    -0.99
     studier
    -0.98
    laştır
    -0.97
     チェ
    -0.96
    POSITIVE LOGITS
     geschickt
    1.13
     Setiap
    1.11
    Abraços
    1.09
     їх
    1.07
     Each
    1.05
     by
    1.04
    melhor
    1.02
    ticides
    1.02
    rystal
    1.02
    }.
    0.99
    Activations Density 0.154%

    No Known Activations