© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 70713
    Prev
    Next
    INDEX
    Explanations

    Objective-C method sender signatures

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

    The neuron fires on occurrences of the identifier “sender” (the method‐parameter name “sender”).

    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
     them
    -1.53
    か月
    -1.52
    ၞ
    -1.52
     Large
    -1.48
    and
    -1.44
     any
    -1.42
     öffnet
    -1.41
    🧌
    -1.40
    </h4>
    -1.37
     anything
    -1.37
    POSITIVE LOGITS
     صنع
    1.52
    ſu
    1.45
                 
    1.40
     hast
    1.38
    显著
    1.34
    droj
    1.34
                   
    1.34
     Comprometido
    1.33
    OUTUBE
    1.30
     Asegúrese
    1.30
    Activations Density 0.001%

    No Known Activations