© 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. 103515
    Prev
    Next
    INDEX
    Explanations

    programming actions and contexts

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

    method calls that retrieve or access data, particularly "get" or "Get" methods.

    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
     kupić
    -1.98
     and
    -1.94
    </h1>
    -1.80
     then
    -1.73
     two
    -1.68
    self
    -1.66
     three
    -1.63
    to
    -1.59
     chose
    -1.59
     reliant
    -1.58
    POSITIVE LOGITS
     sposob
    1.70
    okkal
    1.70
    ientras
    1.69
    ⅝
    1.64
     så
    1.59
    ↵
    1.59
    grandes
    1.55
     ſame
    1.54
    ⅗
    1.51
     entusias
    1.50
    Activations Density 0.010%

    No Known Activations