© 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. 5364
    Prev
    Next
    INDEX
    Explanations

    infamous nightlife

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

    The neuron is selectively activating on unusually rare or low‐frequency content words.

    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
     nahil
    0.91
     lézard
    0.91
    瘓
    0.84
     antagonism
    0.83
    نڈ
    0.79
    ርድ
    0.78
     Wörter
    0.77
    كيت
    0.77
     inodes
    0.76
     मिलीमीटर
    0.76
    POSITIVE LOGITS
    满满
    0.78
    새
    0.75
    나
    0.69
    ↵↵
    0.68
    "/"
    0.68
    grade
    0.65
    Ag
    0.65
    </tbody>
    0.65
     champion
    0.65
    peak
    0.65
    Activations Density 0.000%

    No Known Activations