© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 12950
    Prev
    Next
    INDEX
    Explanations

    event names and places

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

    The neuron fires most strongly on tokens that occur repeatedly in the document—that is, it flags high‐frequency words.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    *
    -3.20
    鯢
    -2.77
    聍
    -2.73
    
    -2.69
    }
    -2.64
    パスタ
    -2.61
    
    -2.58
    鶿
    -2.56
    
    -2.55
    ༀ
    -2.53
    POSITIVE LOGITS
     has
    2.61
    ዡ
    2.44
     ligeramente
    2.44
    鋦
    2.38
     use
    2.31
    ra
    2.25
    ጢ
    2.23
    ⾒
    2.20
     he
    2.19
    最重要的
    2.17
    Activations Density 0.003%

    No Known Activations