© 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. 34-GEMMASCOPE-RES-131K
    7. 49423
    Prev
    Next
    INDEX
    Explanations

    machine learning datasets and Python

    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_34/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
    elementAt
    -1.00
    imbangan
    -0.93
    )&&
    -0.93
     kecelakaan
    -0.90
    Configura
    -0.90
    Spesifikasi
    -0.90
    Imprimir
    -0.85
    Ừ
    -0.85
     Esperanto
    -0.85
    Ironically
    -0.85
    POSITIVE LOGITS
    EDA
    1.55
    cipy
    1.25
     Kag
    1.22
     dataset
    1.17
     Python
    1.16
     insights
    1.16
     pandas
    1.14
    figsize
    1.13
     exploratory
    1.12
     EDA
    1.09
    Activations Density 0.118%

    No Known Activations