© 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. 7484
    Prev
    Next
    INDEX
    Explanations

    public images and servers

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

    The neuron fires strongly on nouns naming commercial products or services (e.g. “swimming pool,” “landscape architect,” “tree removal,” “wedding gown”).

    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
     getAll
    0.68
     fermionic
    0.63
     👌
    0.62
     cationic
    0.62
    hygine
    0.62
     キー
    0.61
     UserService
    0.59
     fdata
    0.59
    rategy
    0.58
     nuanced
    0.58
    POSITIVE LOGITS
     &
    0.68
     and
    0.68
    ikh
    0.64
    ē
    0.63
    -
    0.62
     released
    0.61
     from
    0.60
    +
    0.60
    ansk
    0.58
    列車
    0.56
    Activations Density 0.410%

    No Known Activations