© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 77812
    Prev
    Next
    INDEX
    Explanations

    made available under the terms

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

    The neuron fires most strongly on programming-related identifiers and keywords (names of modules, packages, variables, or API terms).

    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
    的一天
    -0.81
     terminating
    -0.80
     okuyayım
    -0.76
    werker
    -0.73
     triangulation
    -0.72
     τού
    -0.71
    学園
    -0.70
     quotas
    -0.69
     FUNC
    -0.69
     tilting
    -0.69
    POSITIVE LOGITS
     folosit
    0.74
    Curve
    0.72
     générer
    0.71
    Noise
    0.69
     избежать
    0.68
    #/
    0.67
    まります
    0.66
    guard
    0.65
    완
    0.65
     Fossil
    0.62
    Activations Density 0.078%

    No Known Activations