© 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. 31-GEMMASCOPE-2-RES-16K
    7. 6776
    Prev
    Next
    INDEX
    Explanations

    states and conditions

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

    The neuron fires most strongly on content-heavy nouns—especially longer, domain-specific nouns naming key items, concepts, or attributes.

    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_31_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
     ✨
    1.07
     🙌
    1.04
    !"
    1.01
    ✨
    1.00
    💫
    0.94
    Luckily
    0.92
    !'
    0.91
     Luckily
    0.90
     Nowadays
    0.90
    !»
    0.89
    POSITIVE LOGITS
     (
    0.92
     yada
    0.82
     skall
    0.81
     loosing
    0.81
     …..
    0.77
     (%
    0.74
     (?)
    0.74
     ……..
    0.74
    ）（
    0.72
     ವಿರು
    0.72
    Activations Density 0.142%

    No Known Activations