© 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. 22-GEMMASCOPE-RES-131K
    7. 38788
    Prev
    Next
    INDEX
    Explanations

    cube root or cubic measurements

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

    The neuron fires whenever the exact word “Cube” appears.

    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
    
    -3.36
     Você
    -2.59
     Outros
    -2.52
     Até
    -2.42
     Além
    -2.42
    已经
    -2.39
     Importantly
    -2.38
    但
    -2.34
    спомина
    -2.33
     Alguns
    -2.33
    POSITIVE LOGITS
    臯
    2.47
     fuelled
    2.41
     mutfak
    2.33
     Ganzen
    2.28
     gerçekten
    2.19
     nerede
    2.11
    篡
    2.11
    だったが
    2.08
    图为
    2.08
    蔼
    2.06
    Activations Density 0.031%

    No Known Activations