© 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. 75211
    Prev
    Next
    INDEX
    Explanations

    shell scripts and code utilities

    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
    ;
    -2.34
    -
    -2.30
     Following
    -1.90
     When
    -1.88
    what
    -1.76
    =
    -1.67
     собаки
    -1.66
        
    -1.64
    蔓延
    -1.64
     identify
    -1.63
    POSITIVE LOGITS
    sandalia
    2.16
    
    2.14
    踅
    1.91
    TryDecode
    1.88
    jaqueta
    1.82
    sudadera
    1.80
    垕
    1.75
    unità
    1.73
    亖
    1.73
    蒾
    1.70
    Activations Density 0.004%

    No Known Activations