© 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. 102467
    Prev
    Next
    INDEX
    Explanations

    alloc] init

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

    lines of code that allocate and initialize objects using `alloc` and `init` methods.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    This neuron fires on Objective-C message sends—i.e. the `]`-plus-`;` sequences that end method-call expressions.

    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
     メニュー
    -1.98
    時間
    -1.81
     '&
    -1.80
     tormenta
    -1.80
    Ꭳ
    -1.80
    镚
    -1.80
     certains
    -1.78
     ayant
    -1.76
     créer
    -1.75
    ダウン
    -1.74
    POSITIVE LOGITS
     because
    1.92
    as
    1.81
    
    1.80
    gambarkan
    1.77
     that
    1.73
     tenían
    1.72
     podían
    1.66
     from
    1.64
     входят
    1.61
    0
    1.58
    Activations Density 0.008%

    No Known Activations