© 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. 99618
    Prev
    Next
    INDEX
    Explanations

    single characters and code snippets

    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
     nélk
    -0.95
    íma
    -0.91
    だな
    -0.91
     επικ
    -0.89
     \\
    -0.87
    örgy
    -0.86
     dátum
    -0.84
    rát
    -0.82
    今年も
    -0.82
     iniziale
    -0.82
    POSITIVE LOGITS
     was
    0.98
     wasn
    0.91
     not
    0.86
    )
    0.85
    -'
    0.85
    ='
    0.83
    เป็น
    0.79
     furi
    0.79
    ddots
    0.78
     là
    0.77
    Activations Density 0.004%

    No Known Activations