© 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. 77147
    Prev
    Next
    INDEX
    Explanations

    refer to disambiguation

    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
     प्रश्न
    -0.82
    rigkeit
    -0.82
     postdoctoral
    -0.81
     campesinos
    -0.80
    менения
    -0.79
     esimer
    -0.79
     statement
    -0.79
     будете
    -0.76
     مرجع
    -0.75
     new
    -0.74
    POSITIVE LOGITS
     surname
    0.98
     няколко
    0.94
     gleich
    0.94
     may
    0.91
    可能是
    0.90
    obacz
    0.88
     musikk
    0.88
    Também
    0.88
     fictional
    0.86
    还可以
    0.85
    Activations Density 0.154%

    No Known Activations