© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26
    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 22520
    Prev
    Next
    INDEX
    Explanations

    protobuf or related formats

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

    the names “proto,” “buffer,” and “protobuf” (i.e. references to Protocol Buffers) in code and comments.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    -1.48
    beautiful
    -1.39
    er
    -1.24
     same
    -1.23
    powerful
    -1.23
    楽しかった
    -1.19
     même
    -1.14
    
    -1.13
     вось
    -1.13
    ヌーピー
    -1.10
    POSITIVE LOGITS
    }$
    1.40
    鯷
    1.38
     cuisson
    1.26
    مدیر
    1.25
     oggetti
    1.25
    龕
    1.24
    ':
    
    1.23
     menghabiskan
    1.23
     hendak
    1.22
    ໒
    1.22
    Activations Density 0.019%

    No Known Activations