© 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. 60279
    Prev
    Next
    INDEX
    Explanations

    words starting with Cla

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

    The neuron is activated by the letter sequence “Cla” at the start of words (e.g. Claisen, Claudin).

    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
    ❉
    -2.59
     confron
    -2.48
     futura
    -2.38
    
    -2.36
    ⸨
    -2.30
     peristiwa
    -2.30
     contempla
    -2.27
    孓
    -2.23
     foro
    -2.22
     finne
    -2.22
    POSITIVE LOGITS
    1
    3.66
    2
    3.17
    The
    2.91
    2.86
    0
    2.78
     längere
    2.69
    Of
    2.67
     gelesen
    2.52
    ～～～～
    2.48
          
    2.44
    Activations Density 0.003%

    No Known Activations