© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 123723
    Prev
    Next
    INDEX
    Explanations

    rec followed by ruction, ords, or der

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

    the word "rec" or its variations as an abbreviation in technical and medical contexts (such as "record", "recency", "recurrent").

    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
    </u>
    -2.53
     of
    -2.48
    </strong>
    -2.20
     politischen
    -2.14
     et
    -2.14
     verschieden
    -2.08
     technischen
    -2.00
    -
    -2.00
     Hinblick
    -1.99
     好看
    -1.97
    POSITIVE LOGITS
    u
    3.02
    an
    2.25
    begin
    2.02
    end
    2.00
    ”,
    1.98
    össä
    1.98
    ).
    1.90
    rec
    1.90
    mêmes
    1.89
    ціє
    1.89
    Activations Density 0.005%

    No Known Activations