© 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. 22-GEMMASCOPE-RES-131K
    4. 9425
    Prev
    Next
    INDEX
    Explanations

    numbers and variables in equations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     both
    -1.02
     Along
    -0.94
     along
    -0.94
     that
    -0.93
     then
    -0.88
    𝑃
    -0.88
     pytanie
    -0.83
     used
    -0.83
     Both
    -0.83
     ostensibly
    -0.82
    POSITIVE LOGITS
     نیز
    1.12
     тоже
    1.11
     tambien
    1.08
     também
    1.02
     szint
    0.98
     PROVIDE
    0.96
    罍
    0.96
     tercio
    0.95
    顷
    0.93
     анге
    0.93
    Activations Density 0.110%

    No Known Activations