© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 92227
    Prev
    Next
    INDEX
    Explanations

    super senior, Manhattan Airport

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

    The neuron fires on the article’s opening header line—i.e. the comic‐title/issue-number and by‐line metadata (tokens like “#256,” “by,” author names, etc.).

    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
     equ
    -0.72
    érieures
    -0.72
     barra
    -0.72
    ступил
    -0.71
     interna
    -0.70
     Pattaya
    -0.70
     moustache
    -0.69
     Pavia
    -0.68
     яго
    -0.68
     Metropolitana
    -0.68
    POSITIVE LOGITS
     mutant
    1.03
     säs
    0.79
    zeugt
    0.77
    reality
    0.76
     Mutter
    0.75
     televisão
    0.74
     accede
    0.74
    Zunanje
    0.74
     Plains
    0.73
    Mutant
    0.73
    Activations Density 0.011%

    No Known Activations