© 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. 13778
    Prev
    Next
    INDEX
    Explanations

    container or substance

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

    The neuron consistently fires on content nouns naming concrete objects or items.

    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
     lemongrass
    0.65
     enlightenment
    0.64
     없고
    0.63
    และความ
    0.61
     snd
    0.59
     অ্যাল
    0.58
    QMainWindow
    0.58
    𒁉
    0.58
    なかった
    0.57
    стый
    0.57
    POSITIVE LOGITS
    ®.
    0.75
    ™.
    0.62
    。
    0.60
    .
    0.58
    .​​
    0.57
     whose
    0.52
     الذي
    0.52
     instead
    0.51
    °.
    0.51
    instead
    0.51
    Activations Density 0.002%

    No Known Activations