© 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. 44203
    Prev
    Next
    INDEX
    Explanations

    int32 type

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

    This neuron fires on occurrences of the number “32” (e.g. in type names like Int32 or bit‐width specifiers).

    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
    Ilustra
    -1.71
    Karakteristik
    -1.67
    titial
    -1.66
    而
    -1.65
    Способ
    -1.63
    Karakter
    -1.61
    Возраст
    -1.61
     HttpNotFound
    -1.60
    割と
    -1.52
    徜
    -1.52
    POSITIVE LOGITS
     to
    1.83
    o
    1.63
    一会儿
    1.59
    gemar
    1.47
     se
    1.44
    はじめ
    1.40
     has
    1.37
    
    1.37
    zegovina
    1.33
     yaptığı
    1.33
    Activations Density 0.002%

    No Known Activations