© 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. 65585
    Prev
    Next
    INDEX
    Explanations

    rebel, rebellion, defiant attitude

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

    The neuron strongly activates on terms expressing nonconformity or rebellion.

    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
    罒
    -0.92
    alogy
    -0.89
    čila
    -0.89
    celotti
    -0.87
     régl
    -0.87
     مساب
    -0.84
     ſen
    -0.84
    keyup
    -0.84
    amkeit
    -0.82
     morons
    -0.82
    POSITIVE LOGITS
     rebel
    3.59
     rebellion
    3.23
     rebellious
    3.20
    rebel
    2.98
     rebels
    2.91
     Rebel
    2.53
    Rebel
    2.44
     defiance
    2.22
     Rebellion
    2.22
     revolt
    2.22
    Activations Density 0.094%

    No Known Activations