© 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. 3998
    Prev
    Next
    INDEX
    Explanations

    The neuron activates strongly on capitalized proper nouns (names of people, places, events, etc.).

    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
    igde
    0.70
    ৪৩
    0.69
    ET
    0.67
    ৫
    0.66
    ﻰ
    0.66
    나
    0.64
    EOUT
    0.64
    ৫০
    0.64
    έσ
    0.62
    っていない
    0.62
    POSITIVE LOGITS
    अमेरिका
    0.77
    bies
    0.70
    चीनी
    0.67
    י
    0.66
     médicaments
    0.66
     arrhythmias
    0.64
    睞
    0.64
    MIN
    0.64
     benchmarks
    0.64
    hood
    0.64
    Activations Density 3.402%

    No Known Activations