© 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. 34-GEMMASCOPE-RES-131K
    7. 48945
    Prev
    Next
    INDEX
    Explanations

    initializer definitions and calls

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

    The neuron fires strongly on references to UITableView APIs—especially the tableView(_:numberOfRowsInSection:), tableView(_:cellForRowAt:), dequeueReusableCell, and related identifiers—i.e. it detects UITableView-related method signatures and calls.

    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
     類
    -1.04
     Juillet
    -0.90
    …？
    -0.88
    ďaka
    -0.87
    🚼
    -0.86
     燒
    -0.83
    ⊇
    -0.83
     permettre
    -0.79
     圓
    -0.79
     “[
    -0.77
    POSITIVE LOGITS
    (_
    2.48
     (_
    1.88
     _
    1.73
     $\
    1.59
    >(_
    1.54
    =_
    1.41
    ,_
    1.32
    ->_
    1.22
    [_
    1.20
     [_
    1.19
    Activations Density 0.010%

    No Known Activations