© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 15119
    Prev
    Next
    INDEX
    Explanations

    social media, crypto, cybersecurity, wildlife photography

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

    The neuron strongly activates on isolated metadata‐style labels—capitalized section titles, numbered or hashtagged tags, and other heading tokens—rather than ordinary running text.

    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
     R
    1.11
     M
    1.04
     L
    1.04
     S
    1.03
     V
    1.03
     E
    1.02
     F
    1.00
     P
    1.00
     N
    0.98
     Service
    0.96
    POSITIVE LOGITS
    ofinstagram
    1.31
    스타그램
    1.16
    instagood
    1.01
    christmas
    0.99
    してる
    0.98
    stagram
    0.98
    ♥️
    0.97
     méxico
    0.97
    friday
    0.96
    poetrycommunity
    0.92
    Activations Density 0.964%

    No Known Activations