© 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. 69977
    Prev
    Next
    INDEX
    Explanations

    software generation metadata

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

    The neuron fires on numeric literal tokens (e.g. version numbers or other standalone numbers).

    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
    šia
    -0.88
    ってない
    -0.85
     habt
    -0.85
    ってみる
    -0.82
    はや
    -0.79
     organizacji
    -0.79
     витами
    -0.79
    ifique
    -0.79
    ないです
    -0.79
     hate
    -0.77
    POSITIVE LOGITS
     System
    1.20
     Microsoft
    0.98
    #,
    0.91
    System
    0.89
    Microsoft
    0.89
    Generated
    0.89
    ٔ
    0.87
     entendu
    0.82
     néanmoins
    0.82
    ებ
    0.81
    Activations Density 0.004%

    No Known Activations