© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 101479
    Prev
    Next
    INDEX
    Explanations

    conditional return statements

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

    indentation or whitespace at the beginning of code blocks, particularly after conditional statements or function declarations.

    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
    よりも
    -1.35
     nejen
    -1.31
     rather
    -1.28
     not
    -1.26
     ultimately
    -1.23
    UNGEN
    -1.22
     некото
    -1.20
    ívne
    -1.19
     plutôt
    -1.18
     không
    -1.16
    POSITIVE LOGITS
     nor
    1.64
     anymore
    1.56
     because
    1.45
    。“
    1.25
    。
    1.24
    ，“
    1.19
    andExpect
    1.18
     enää
    1.18
     due
    1.17
     sondern
    1.17
    Activations Density 0.008%

    No Known Activations