© 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. 54228
    Prev
    Next
    INDEX
    Explanations

    must reproduce

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

    code license text in programming files, particularly sections about reproduction and redistribution requirements.

    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
     not
    -1.25
     have
    -1.08
     decreases
    -1.05
    ấm
    -1.04
    JAMIN
    -1.02
     uſed
    -1.02
     then
    -1.01
    :%.
    -1.01
    capai
    -0.99
    ",
    -0.98
    POSITIVE LOGITS
     ebenfalls
    1.53
     ähnlichen
    1.16
    ↵↵↵↵↵↵↵↵↵↵
    1.10
     tampoco
    1.09
     solchen
    1.05
     gleichen
    1.04
     igualmente
    1.03
     dieselben
    1.02
     famed
    1.02
    ↵↵↵↵↵↵↵↵↵↵↵↵↵
    1.01
    Activations Density 0.022%

    No Known Activations