© 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. 8353
    Prev
    Next
    INDEX
    Explanations

    positive, endearing, and cute descriptors

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

    The neuron responds strongly to adjectives and intensifiers that express cuteness or adorableness (e.g. “cute,” “adorable,” “darling”).

    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
    <unused8>
    0.84
    సూరు
    0.80
     промышлен
    0.77
     прежде
    0.76
     vervolgens
    0.76
     familles
    0.75
     équ
    0.75
    শিল্প
    0.74
     foodservice
    0.74
    ⓵
    0.73
    POSITIVE LOGITS
     cute
    1.25
     adorable
    1.09
     Cute
    1.07
     quirky
    0.97
     lindos
    0.97
     chibi
    0.96
    Cute
    0.96
     かわいい
    0.94
     cheesy
    0.94
     girly
    0.91
    Activations Density 0.011%

    No Known Activations