© 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. 86317
    Prev
    Next
    INDEX
    Explanations

    Beatles and Ringo Starr

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

    The neuron fires on mentions of the rock band “The Beatles” (and its members’ names).

    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
    ."
    -3.13
    ?
    -3.06
    ).
    -2.70
    onViewCreated
    -2.53
    錞
    -2.48
    
    -2.44
    PerformLayout
    -2.41
    EndInit
    -2.28
    lapsingToolbar
    -2.28
     岛
    -2.27
    POSITIVE LOGITS
    mm
    2.45
     zwölf
    2.31
    ts
    2.31
    ”،
    2.28
    蟊
    2.23
    푉
    2.23
     〜
    2.19
     nuovo
    2.17
     Перейти
    2.17
    </h1>
    2.13
    Activations Density 0.002%

    No Known Activations