© 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-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 15946
    Prev
    Next
    INDEX
    Explanations

    therapist or counselor

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

    The neuron is triggered by distinctive, content‐bearing terms—especially proper nouns, technical labels, or domain‐specific keywords.

    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
     altri
    0.77
     antics
    0.74
    今まで
    0.73
     anta
    0.73
     संयोजक
    0.72
    );
    0.71
     majors
    0.71
     antiques
    0.71
     coasts
    0.71
     mano
    0.70
    POSITIVE LOGITS
     данных
    0.92
    rijke
    0.85
     আর্থিক
    0.83
    omh
    0.82
    ❐
    0.81
    achter
    0.80
    lı
    0.79
     आकलन
    0.79
     уйнау
    0.79
     రెండు
    0.78
    Activations Density 0.000%

    No Known Activations