© 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. 40890
    Prev
    Next
    INDEX
    Explanations

    kitten and kitchen

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

    The neuron strongly activates on the character sequence “kit” (e.g. in “kitten,” “Atomic Kitten,” “mittens,” “kitchen”).

    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
    
    -2.55
    瓩
    -2.53
    เกง
    -2.53
    戩
    -2.44
    .......
    -2.41
    。。。。
    -2.39
    бет
    -2.36
    袮
    -2.33
     cuillère
    -2.31
    ......
    -2.30
    POSITIVE LOGITS
    へ向
    2.34
    ᠂
    2.33
     дети
    2.31
    我又
    2.31
     buscando
    2.30
     conhecida
    2.25
    刖
    2.23
     […]
    2.20
     nothwendig
    2.20
     but
    2.19
    Activations Density 0.001%

    No Known Activations