© 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. 10-GEMMASCOPE-RES-131K
    7. 112713
    Prev
    Next
    INDEX
    Explanations

    object sender

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

    This neuron activates specifically on the keyword “object” when it appears as a type in method‐parameter declarations.

    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
    鹇
    -1.84
    
    -1.80
    licopter
    -1.70
     oferec
    -1.68
     galería
    -1.64
     permitan
    -1.59
    ಱ
    -1.59
     薬局
    -1.56
     '
    -1.55
    臜
    -1.53
    POSITIVE LOGITS
    }
    1.58
    ğim
    1.54
    </h3>
    1.52
    Perhaps
    1.51
     and
    1.49
     ""],
    1.48
    Before
    1.48
    Despite
    1.45
    When
    1.44
    黽
    1.43
    Activations Density 0.001%

    No Known Activations