© 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. 20557
    Prev
    Next
    INDEX
    Explanations

    acronyms for organizations

    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
    ;
    -1.86
     with
    -1.57
     including
    -1.55
    !
    -1.51
    我去
    -1.47
    ?
    -1.47
    h
    -1.45
     on
    -1.44
    .
    -1.41
    ville
    -1.41
    POSITIVE LOGITS
    bilità
    1.88
     dieser
    1.76
     hinder
    1.68
    ↵↵
    1.55
    นาด
    1.54
    
    1.51
    Уже
    1.48
    𝜖
    1.47
    یمت
    1.45
    Historically
    1.45
    Activations Density 0.183%

    No Known Activations