© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 8914
    Prev
    Next
    INDEX
    Explanations

    adjectives describing qualities

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

    The neuron activates most strongly on descriptive, evaluative adjectives and adverbs (intensifiers and opinion-bearing modifiers).

    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
    Alternatively
    0.79
    Ͻ
    0.61
    Compatibility
    0.58
    或其他
    0.58
    或
    0.58
    compatibility
    0.57
    再び
    0.57
    opro
    0.57
    や
    0.57
    its
    0.56
    POSITIVE LOGITS
     workman
    0.98
     travaille
    0.91
     agréable
    0.89
     அழகான
    0.89
     affaires
    0.87
     plenty
    0.87
     mooie
    0.85
     อะไร
    0.85
     enjoyable
    0.84
     sicuramente
    0.83
    Activations Density 0.614%

    No Known Activations