© 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. 22-GEMMASCOPE-RES-131K
    7. 98589
    Prev
    Next
    INDEX
    Explanations

    package names, names, science terms

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

    indentation or whitespace at the beginning of code and document lines.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
     their
    -1.37
     it
    -1.25
     not
    -1.05
     even
    -0.98
    ärin
    -0.96
     sorta
    -0.95
     It
    -0.94
     mögen
    -0.94
     both
    -0.92
     without
    -0.92
    POSITIVE LOGITS
     culturale
    1.25
     unele
    1.15
     fondamentale
    1.12
     někter
    1.11
    այի
    1.05
    astrar
    1.03
    を行い
    1.02
     giacca
    1.02
     alimentare
    1.01
     gän
    0.98
    Activations Density 0.000%

    No Known Activations