© 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. 10-GEMMASCOPE-RES-131K
    4. 102257
    Prev
    Next
    INDEX
    Explanations

    variables named one and two

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

    the digit "2" when it appears as a numeric suffix or index in variable names, function parameters, or list identifiers (like "num2", "List2", "str_2").

    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
     a
    -1.47
     Vielzahl
    -1.34
    camento
    -1.27
    +++++
    -1.24
    Материал
    -1.21
    Форма
    -1.20
    Читать
    -1.17
     in
    -1.17
     êtes
    -1.14
    chair
    -1.13
    POSITIVE LOGITS
     which
    1.95
     waarbij
    1.53
     It
    1.33
     sguardo
    1.29
     varandra
    1.26
     namely
    1.25
     blazing
    1.23
     oscu
    1.23
     它
    1.23
    Blockly
    1.21
    Activations Density 0.035%

    No Known Activations