© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 2129
    Prev
    Next
    INDEX
    Explanations

    qualities and excellence

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

    This neuron detects strongly positive descriptive praise—complimentary adjectives and superlatives applied to people’s performances, talents, or skills.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     information
    0.70
     scenarios
    0.70
     implica
    0.68
     informasi
    0.67
     blobs
    0.65
     conditions
    0.64
     información
    0.64
    /
    0.64
     INFORMATION
    0.64
    的情况
    0.64
    POSITIVE LOGITS
     талант
    0.98
     charisma
    0.96
     उत्कृष्ट
    0.94
     prowess
    0.92
     acumen
    0.91
     artistry
    0.88
     enviable
    0.86
     superbly
    0.86
     Traits
    0.85
    charisma
    0.84
    Activations Density 0.245%

    No Known Activations