© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 11642
    Prev
    Next
    INDEX
    Explanations

    such, answers, stdlib

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

    technical or formal terminology, particularly words that end in common suffixes like "-to", "-frac", "stdlib", or words like "such", "answers", "agent", and "train" in specialized technical, scientific, or formal contexts.

    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
    because
    -1.34
    却被
    -1.31
     EXPER
    -1.30
     mahdol
    -1.30
    porque
    -1.29
    commented
    -1.28
    something
    -1.27
     Luís
    -1.27
     古风
    -1.27
    JMenuItem
    -1.26
    POSITIVE LOGITS
     on
    1.48
     they
    1.31
     use
    1.30
     plus
    1.28
     R
    1.27
     no
    1.26
     add
    1.24
     always
    1.23
     about
    1.22
     T
    1.20
    Activations Density 0.134%

    No Known Activations