© 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. 109286
    Prev
    Next
    INDEX
    Explanations

    binary and character sequences

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

    The neuron flags long runs of repeated non-letter characters (ASCII-art or diagram blocks) in code or text snippets.

    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
     what
    -1.07
     because
    -0.87
     those
    -0.86
     that
    -0.86
     obuv
    -0.85
    Yeni
    -0.84
     kár
    -0.82
    ṕ
    -0.82
     an
    -0.80
     ellers
    -0.80
    POSITIVE LOGITS
    lebnis
    0.96
    味的
    0.90
    将在
    0.89
    ernalia
    0.88
    urer
    0.88
     другой
    0.88
     tableta
    0.87
     другое
    0.86
    ఽ
    0.85
    
    0.84
    Activations Density 0.014%

    No Known Activations