© 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. 6461
    Prev
    Next
    INDEX
    Explanations

    type of programming construct

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

    The neuron activates strongly on words that are part of named products or media titles (e.g. device model cases, book or article titles).

    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
    ﺑ
    0.88
    पी
    0.87
    ﻓ
    0.87
    택
    0.82
    就算
    0.82
    ﻋ
    0.81
     gaat
    0.80
    TCP
    0.79
    REACT
    0.79
     esimerkiksi
    0.79
    POSITIVE LOGITS
    amento
    0.84
    ları
    0.82
    de
    0.80
    ament
    0.78
    rous
    0.78
    e
    0.77
    eni
    0.77
     Change
    0.77
     purpure
    0.77
    don
    0.75
    Activations Density 0.001%

    No Known Activations