© 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. 10-GEMMASCOPE-RES-131K
    7. 12323
    Prev
    Next
    INDEX
    Explanations

    initialization and conditional checks

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

    variable names in programming code, especially those used in conditional statements or assignments.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     vinil
    -1.51
     conster
    -1.38
     illimit
    -1.34
     تمامی
    -1.30
     diamant
    -1.30
     Dirección
    -1.28
     vitrine
    -1.28
     Alamofire
    -1.27
     colch
    -1.27
     horloge
    -1.27
    POSITIVE LOGITS
    There
    1.44
     one
    1.42
     saludable
    1.40
    Sometimes
    1.38
    If
    1.26
    One
    1.21
     sometimes
    1.21
     if
    1.19
    Even
    1.17
    Are
    1.16
    Activations Density 0.042%

    No Known Activations