© 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. 109470
    Prev
    Next
    INDEX
    Explanations

    health literature and stripping

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

    company or organization names and references in text.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron activates on numeric tokens, especially multi‐digit 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
     two
    -0.81
    trung
    -0.77
    kinh
    -0.74
     unieke
    -0.74
     by
    -0.74
     or
    -0.73
     three
    -0.73
    ('-'
    -0.73
     helps
    -0.73
     Creating
    -0.72
    POSITIVE LOGITS
    unch
    1.11
    otations
    0.96
     quotations
    0.95
    London
    0.91
     London
    0.90
    corresponding
    0.90
     unchanged
    0.88
    atized
    0.88
    лар
    0.85
     firmness
    0.85
    Activations Density 0.000%

    No Known Activations