© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 75466
    Prev
    Next
    INDEX
    Explanations

    octa- prefixes

    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
    estation
    -0.86
    метра
    -0.82
    Tamil
    -0.80
    flexGrow
    -0.78
     Belakang
    -0.77
    thin
    -0.77
    plained
    -0.76
    ̓
    -0.75
    epa
    -0.75
    )');
    -0.75
    POSITIVE LOGITS
     Hex
    0.94
     Oct
    0.93
     Octa
    0.90
    Oct
    0.80
    美
    0.79
     slay
    0.78
     any
    0.76
     oct
    0.75
    dec
    0.75
    try
    0.73
    Activations Density 0.040%

    No Known Activations