© 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. 108596
    Prev
    Next
    INDEX
    Explanations

    code, spiritual discourses, yoga

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

    The neuron fires on title‐style or heading tokens—capitalized words, numbers, punctuation, and proper names that occur in section or article titles.

    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
     Enrico
    -0.78
     shadows
    -0.77
     agreed
    -0.76
     tokyo
    -0.75
    嗅
    -0.74
     allah
    -0.73
     Siamese
    -0.73
     Berner
    -0.73
     dou
    -0.73
     atto
    -0.71
    POSITIVE LOGITS
     Falun
    0.98
     humanitarian
    0.84
     spiritual
    0.83
    International
    0.82
     dano
    0.81
     soltar
    0.81
     Os
    0.81
     meditation
    0.78
    kesan
    0.77
     discourses
    0.75
    Activations Density 0.033%

    No Known Activations