© 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. 84962
    Prev
    Next
    INDEX
    Explanations

    scuba diving, Scrum training

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

    The neuron strongly responds to the character sequence “scu” (as found in words like scuff, scuba, scrum, scutils, etc.).

    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
    我们在
    -2.77
    谖
    -2.44
    豨
    -2.44
    獴
    -2.33
    ୩
    -2.31
     Mitgliedern
    -2.27
    缡
    -2.27
    킁
    -2.25
     Jugendlichen
    -2.22
    isait
    -2.22
    POSITIVE LOGITS
    "
    3.06
    ’
    2.59
    ↵
    2.31
    am
    2.20
    replyreport
    2.03
     verbreitet
    2.02
     unsur
    1.95
     ideally
    1.95
    ,—
    1.84
    értelmű
    1.83
    Activations Density 0.004%

    No Known Activations