© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 78939
    Prev
    Next
    INDEX
    Explanations

    public or export class

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

    The neuron strongly activates on the keyword “public” (the public‐access modifier) in code.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    עס
    -0.84
    遛
    -0.82
    InfoService
    -0.82
    쳤
    -0.82
     ešte
    -0.82
    cline
    -0.81
    مقاله
    -0.80
     жі
    -0.80
     it
    -0.79
    のお知らせ
    -0.79
    POSITIVE LOGITS
     וח
    0.91
    етесь
    0.85
     uomini
    0.82
    _{
    0.82
    minin
    0.82
    ismatic
    0.81
    рованного
    0.81
    க
    0.80
    illeur
    0.80
    ditch
    0.80
    Activations Density 0.004%

    No Known Activations