© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 39680
    Prev
    Next
    INDEX
    Explanations

    Objective-C selectors or `send`

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    ”,
    -1.58
    ➡️
    -1.54
     there
    -1.48
     ‘‘
    -1.40
    </i>
    -1.40
     perfectos
    -1.37
    وروبا
    -1.36
     ‘
    -1.35
    出てくる
    -1.34
    StoryboardSegue
    -1.32
    POSITIVE LOGITS
    
    1.70
    豋
    1.66
     impec
    1.57
     répondre
    1.45
    廰
    1.43
    𐄙
    1.42
     attività
    1.38
    .&
    1.36
     entiende
    1.35
    渽
    1.34
    Activations Density 0.004%

    No Known Activations