© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 83783
    Prev
    Next
    INDEX
    Explanations

    codes and identifiers

    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
     número
    -0.88
    号码
    -0.85
    firmasi
    -0.82
     Wednesday
    -0.75
     berbeda
    -0.73
    number
    -0.73
    different
    -0.73
    splatz
    -0.72
     números
    -0.72
     aluno
    -0.72
    POSITIVE LOGITS
     code
    2.83
     codes
    2.61
    code
    2.27
    代码
    2.27
     Code
    2.20
    Code
    2.17
    コード
    2.14
     código
    2.05
     Codes
    2.00
     код
    1.93
    Activations Density 0.050%

    No Known Activations