© 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-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 35699
    Prev
    Next
    INDEX
    Explanations

    hard 7.x branch

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

    The neuron activates on numeric tokens (e.g. list numbers, years, citation indices, and other digits).

    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
     pageNo
    -1.04
    ⴱ
    -1.00
     assailed
    -0.90
    젼
    -0.88
    OLIC
    -0.88
    Välislingid
    -0.88
     custa
    -0.87
     aksesuar
    -0.85
     élar
    -0.85
     rozší
    -0.85
    POSITIVE LOGITS
    orcid
    0.93
     Ocak
    0.87
    ],
    
    0.85
     października
    0.81
    Technik
    0.79
    "+
    
    0.78
     on
    0.77
    邯
    0.77
     or
    0.76
    ınız
    0.76
    Activations Density 0.192%

    No Known Activations