© 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. 103434
    Prev
    Next
    INDEX
    Explanations

    epsilon

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

    The neuron flags very common function words and structural tokens (e.g. “the,” “by,” “using,” “of,” “every,” “exists,” “delta,” etc.).

    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
     Cyclops
    -0.74
     Remember
    -0.66
     Experienced
    -0.65
    routers
    -0.64
     ov
    -0.64
    峯
    -0.63
    networking
    -0.63
    jö
    -0.63
    正直
    -0.62
     beautiful
    -0.62
    POSITIVE LOGITS
     epsilon
    3.44
    epsilon
    3.33
    varepsilon
    3.03
     ε
    3.02
     eps
    2.86
     Epsilon
    2.70
    ε
    2.67
    eps
    2.63
    Epsilon
    2.44
    ϵ
    2.38
    Activations Density 0.060%

    No Known Activations