© 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
    2. Gemma-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 5333
    Prev
    Next
    INDEX
    Explanations

    abbreviations like SMS, SIM, BL

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

    The neuron activates on short all-caps letter sequences—that is, acronyms or initialisms.

    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
    Hash
    0.39
    HASH
    0.35
    लेंट
    0.33
     Hash
    0.33
    Scalar
    0.33
    NEXT
    0.32
    㧿
    0.32
    HashTable
    0.31
    iz
    0.31
    ']}
    0.31
    POSITIVE LOGITS
     או
    0.34
    ්
    0.32
    🅴
    0.31
     بال
    0.31
     amoureux
    0.31
     מה
    0.31
     लगाकर
    0.30
     Diarsipkan
    0.30
     ל
    0.30
     ומ
    0.29
    Activations Density 0.000%

    No Known Activations