© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 41014
    Prev
    Next
    INDEX
    Explanations

    Western diet

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

    uppercase letter sequences or abbreviations.

    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_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
     and
    -2.38
     by
    -2.05
     as
    -1.80
     after
    -1.73
     because
    -1.72
     on
    -1.63
     tells
    -1.60
     with
    -1.59
     or
    -1.59
     perplexing
    -1.56
    POSITIVE LOGITS
    峮
    2.17
    Seems
    1.90
    ––
    1.87
    
    1.83
    殽
    1.73
     elegantly
    1.71
    .”
    1.69
    Hmmm
    1.67
    </strong>
    1.66
    に入れる
    1.66
    Activations Density 0.000%

    No Known Activations