© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 87033
    Prev
    Next
    INDEX
    Explanations

    volcano nachos, octopus URL, compass definition, Columbus breeds

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

    The neuron strongly activates on appearances of the word “octopus” (in any casing or split across sub‐tokens).

    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
    猡
    -3.66
    ࿆
    -3.14
    ༀ
    -3.06
    
    -3.06
    艄
    -3.05
    诹
    -2.89
    矬
    -2.88
    irected
    -2.88
     新款
    -2.81
    彀
    -2.80
    POSITIVE LOGITS
    It
    3.45
    7
    3.30
    8
    3.02
    a
    2.98
    {
    2.98
    d
    2.89
     *
    2.81
     )
    2.81
    e
    2.77
    4
    2.72
    Activations Density 0.013%

    No Known Activations