© 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-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 612
    Prev
    Next
    INDEX
    Explanations

    e.g. (A))

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

    The neuron detects uppercase abbreviations or acronyms (all-caps letter sequences).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     aliviar
    -1.33
    いかがでしたか
    -1.29
     encuent
    -1.29
     oxígeno
    -1.23
     this
    -1.22
     thofe
    -1.21
    ところで
    -1.20
    ⃨
    -1.20
     beteken
    -1.20
     our
    -1.20
    POSITIVE LOGITS
    n
    1.38
            
    1.30
                
    1.26
     ハーフ
    1.23
    an
    1.23
    渼
    1.20
    AL
    1.16
     shimmering
    1.16
    ↵
    1.14
    ak
    1.14
    Activations Density 0.336%

    No Known Activations