© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 102846
    Prev
    Next
    INDEX
    Explanations

    action verbs in code statements

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

    camelCase variable or function names in programming code, particularly when they contain the word "To" in the middle.

    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
     helps
    -1.48
     one
    -1.48
    t
    -1.41
     delivers
    -1.32
    p
    -1.30
    and
    -1.29
     two
    -1.28
     will
    -1.26
     what
    -1.23
     provides
    -1.22
    POSITIVE LOGITS
    ه
    1.64
    geschoss
    1.47
    istischen
    1.42
     también
    1.42
    wisata
    1.40
     également
    1.39
     Това
    1.39
    ynchronously
    1.38
    أس
    1.38
     также
    1.38
    Activations Density 0.009%

    No Known Activations