© 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. 98712
    Prev
    Next
    INDEX
    Explanations

    build directives

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

    The neuron selectively activates on numeric literals (digit sequences) 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
    𝗇
    -0.84
    FEL
    -0.83
    ◁
    -0.82
     rezerv
    -0.81
    Quan
    -0.78
     wyma
    -0.77
    لمة
    -0.77
     tronco
    -0.76
     vainilla
    -0.76
     chré
    -0.75
    POSITIVE LOGITS
     murmurs
    0.85
     stringent
    0.82
    lers
    0.79
     мере
    0.79
     グッズ
    0.78
    therefore
    0.76
    IPs
    0.76
    ̵
    0.74
    eneral
    0.74
     laughs
    0.74
    Activations Density 0.000%

    No Known Activations