© 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. 49032
    Prev
    Next
    INDEX
    Explanations

    Amiga computer platform

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron strongly activates on code-style or technical documentation snippets—especially those containing version numbers, numeric literals, and software/hardware identifiers like “Amiga.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     compound
    -0.92
    compound
    -0.81
    ujte
    -0.73
    ører
    -0.72
     Compound
    -0.69
    länder
    -0.69
    Limiter
    -0.68
    Compound
    -0.68
     mę
    -0.67
     rús
    -0.67
    POSITIVE LOGITS
     Amiga
    1.48
     Intuition
    1.11
     AGA
    1.04
    UAE
    1.02
     amig
    0.95
     Ami
    0.93
    Ami
    0.93
     amiga
    0.91
     HDF
    0.91
     UAE
    0.90
    Activations Density 0.045%

    No Known Activations