© 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. 19414
    Prev
    Next
    INDEX
    Explanations

    scout team, scouts, scouting combine, Scout Finch, Indian Scout

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

    The neuron fires on any form of the word “scout” (including “scouting,” “scouts,” “Scout Team,” 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
     When
    -2.34
     divertidas
    -2.09
    ↵↵
    -2.06
     Remember
    -2.03
     Allowing
    -2.02
     Considering
    -2.00
    when
    -1.97
    我们在
    -1.93
                
    -1.92
     när
    -1.92
    POSITIVE LOGITS
    戋
    2.64
    ㉗
    2.38
    an
    2.38
    厛
    2.34
     jj
    2.33
    ዡ
    2.31
    亹
    2.30
     abbildung
    2.27
     returning
    2.22
    änemark
    2.22
    Activations Density 0.004%

    No Known Activations