© 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. 22-GEMMASCOPE-RES-131K
    7. 70740
    Prev
    Next
    INDEX
    Explanations

    public keyword

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

    The neuron fires on numeric constants (digits or numbers) 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_22/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
     voient
    -0.99
     daar
    -0.98
     剑
    -0.93
    Responsible
    -0.91
     manqué
    -0.91
    ugges
    -0.91
     gratuite
    -0.88
    Į
    -0.88
     poeta
    -0.87
    considered
    -0.87
    POSITIVE LOGITS
     or
    0.97
     changes
    0.85
     situazione
    0.82
    ppone
    0.81
     либо
    0.79
    Some
    0.79
     may
    0.79
    ່
    0.79
    ندية
    0.78
     vectorial
    0.78
    Activations Density 0.004%

    No Known Activations