© 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. 12312
    Prev
    Next
    INDEX
    Explanations

    read-only memory or access

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

    the term "readonly" or "read only" in programming and technical 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
    蓠
    -2.33
    geſ
    -1.97
    鹀
    -1.86
     to
    -1.79
     wortel
    -1.76
      
    -1.73
     '>=
    -1.68
    鸸
    -1.67
     必
    -1.63
    嚒
    -1.63
    POSITIVE LOGITS
    灩
    2.23
    If
    2.19
    Ні
    2.08
    9
    2.03
    you
    1.99
    。
    1.98
    We
    1.98
    This
    1.98
    8
    1.97
    For
    1.85
    Activations Density 0.009%

    No Known Activations