© 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. 9482
    Prev
    Next
    INDEX
    Explanations

    programming method names

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

    The neuron peaks on “get” method calls (i.e. API calls beginning with the token “get”).

    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
    スポンサーリンク
    -1.75
    when
    -1.70
    to
    -1.63
    ではでは
    -1.58
    they
    -1.50
    时候
    -1.39
     both
    -1.38
    mathrm
    -1.37
    なども
    -1.35
    although
    -1.34
    POSITIVE LOGITS
     tín
    1.60
     homicidio
    1.55
     jardim
    1.45
     its
    1.43
     divertidos
    1.42
     escritores
    1.41
    ческом
    1.40
     giocatore
    1.35
     nieuwe
    1.33
     amazing
    1.32
    Activations Density 0.005%

    No Known Activations