© 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. 123765
    Prev
    Next
    INDEX
    Explanations

    structured data snippets

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

    whitespace or formatting characters, particularly spaces and tabs at the beginning of lines or between code/data elements.

    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
    0
    -2.23
    1
    -1.82
    “
    -1.81
    -1.74
    Might
    -1.74
     oppure
    -1.74
    n
    -1.73
      
    -1.67
     What
    -1.66
     same
    -1.66
    POSITIVE LOGITS
    );
    2.03
    щита
    1.91
    ))),
    1.88
    droj
    1.84
    癀
    1.77
    鱟
    1.77
    dehydes
    1.74
    تیجه
    1.71
    AutoresizingMask
    1.71
    งิน
    1.70
    Activations Density 0.000%
    No Known Activations