© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 92254
    Prev
    Next
    INDEX
    Explanations

    javascript require statements.NET configurationcompiler arguments

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

    The neuron activates on numeric literals—i.e. tokens composed of digits (numbers) in the document.

    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
     Pompe
    -0.76
    ETHER
    -0.74
     tpl
    -0.71
     tuff
    -0.71
     easterly
    -0.69
     circumscribed
    -0.68
    𝓉
    -0.68
     Cm
    -0.68
     memoranda
    -0.68
    BATCH
    -0.67
    POSITIVE LOGITS
    essment
    0.76
    ưỡi
    0.71
    杆
    0.68
     lançado
    0.67
    救命
    0.66
    尹
    0.65
    penters
    0.65
     לה
    0.65
     consiste
    0.65
    Nguồn
    0.64
    Activations Density 0.068%

    No Known Activations