© 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. 11054
    Prev
    Next
    INDEX
    Explanations

    get property or method calls

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

    method calls and property accesses (dots followed by method or property names) 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
     zaraz
    -1.28
    Especies
    -1.21
    verstanden
    -1.20
    癡
    -1.20
    Hå
    -1.18
    cyjnych
    -1.13
    時候
    -1.13
    Ꮓ
    -1.12
    WireFormat
    -1.11
    artement
    -1.09
    POSITIVE LOGITS
    ḿ
    1.35
    儅
    1.31
     geschikt
    1.30
    ,
    1.27
     its
    1.14
    }
    1.06
     [
    1.05
     has
    1.03
     in
    1.02
    我又
    1.02
    Activations Density 0.110%

    No Known Activations