© 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. 31-GEMMASCOPE-2-RES-16K
    7. 74
    Prev
    Next
    INDEX
    Explanations

    several popular types

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

    The neuron fires on generalizing/distributive quantifier terms (e.g. “every,” “each,” “any,” “one”).

    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_31_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
    H
    0.30
    B
    0.29
    C
    0.28
    Both
    0.27
    Name
    0.27
    Only
    0.27
    W
    0.26
    K
    0.26
    E
    0.26
    V
    0.26
    POSITIVE LOGITS
     aspects
    0.51
     facets
    0.49
     jurisdictions
    0.48
     kinds
    0.48
     sectors
    0.47
     conceivable
    0.47
     aspekt
    0.47
     countries
    0.46
     nations
    0.46
     avenues
    0.45
    Activations Density 1.251%

    No Known Activations