© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 89792
    Prev
    Next
    INDEX
    Explanations

    ( followed by code constructs

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

    The neuron activates on numeric literals (e.g. integer values) in code.

    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
    筷子
    -0.77
     Doppel
    -0.74
     consejos
    -0.67
     Companion
    -0.65
    PublicKey
    -0.65
    delig
    -0.65
     PlayStation
    -0.64
     Xbox
    -0.64
    емся
    -0.64
    Companion
    -0.64
    POSITIVE LOGITS
    шна
    0.68
     flare
    0.67
     scot
    0.64
     nether
    0.64
     Flare
    0.63
    czeń
    0.63
     μια
    0.63
    Concepto
    0.63
    új
    0.62
     gluing
    0.62
    Activations Density 0.060%

    No Known Activations