© 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. 8669
    Prev
    Next
    INDEX
    Explanations

    words starting with Ka

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

    The neuron fires on the two‐letter sequence “Ka,” especially when it appears as a standalone token or name prefix.

    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
    ↵↵
    -3.88
    </h3>
    -3.05
    m
    -2.61
    我的
    -2.59
    ens
    -2.59
    by
    -2.59
     моя
    -2.55
     ),
    -2.50
    al
    -2.44
    la
    -2.36
    POSITIVE LOGITS
    Πηγή
    2.50
    鲔
    2.45
     标志
    2.42
    𓍊
    2.39
    残酷
    2.34
     nadru
    2.25
    0
    2.23
     dwindling
    2.20
     ooit
    2.20
     capucha
    2.20
    Activations Density 0.005%

    No Known Activations