© 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. 119839
    Prev
    Next
    INDEX
    Explanations

    mapping lambda functions

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

    the lambda arrow operator (=>) in programming code.

    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
     hjelp
    -1.73
     medlemmer
    -1.68
    idable
    -1.65
    ֪
    -1.59
     navnet
    -1.52
     hjælp
    -1.50
    titu
    -1.48
     bygge
    -1.42
    瞒
    -1.41
     anledning
    -1.39
    POSITIVE LOGITS
     when
    1.55
     beliebtesten
    1.52
     that
    1.52
     häufigsten
    1.45
     Ähn
    1.41
     to
    1.34
     Können
    1.32
    ilever
    1.27
     at
    1.25
     Tatsache
    1.23
    Activations Density 0.039%

    No Known Activations