© 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. 119705
    Prev
    Next
    INDEX
    Explanations

    code identifiers and short words

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

    single lowercase letters, especially in technical or code contexts where they are used as variable names or identifiers.

    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
    ↵↵
    -2.05
    in
    -1.72
    or
    -1.46
     había
    -1.42
    ↵
    -1.36
     “
    -1.34
     aveva
    -1.31
    ↵↵↵
    -1.30
    and
    -1.30
     another
    -1.27
    POSITIVE LOGITS
     getUserId
    1.76
    cologist
    1.75
     itemprop
    1.65
    titial
    1.65
    providedIn
    1.64
     {
    1.63
    inthians
    1.62
    domada
    1.58
     EconPapers
    1.56
    
    1.55
    Activations Density 0.268%

    No Known Activations