© 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. 624
    Prev
    Next
    INDEX
    Explanations

    chants and protests

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

    The neuron detects occurrences of chanting or slogan‐style quoted rally cries (e.g. “Hands up, guns down” and other protest chants).

    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
    렴
    -0.90
     createContext
    -0.82
     "...
    -0.80
     “...
    -0.77
    اة
    -0.76
    لام
    -0.75
     maîtrise
    -0.74
    ilius
    -0.74
     ≥
    -0.74
     venezol
    -0.73
    POSITIVE LOGITS
     chants
    1.40
     chant
    1.32
     chanted
    1.28
     chanting
    1.13
     slogans
    0.92
    χος
    0.85
     unity
    0.85
    united
    0.83
    chant
    0.83
    shame
    0.82
    Activations Density 0.012%

    No Known Activations