© 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. 34-GEMMASCOPE-RES-131K
    7. 7295
    Prev
    Next
    INDEX
    Explanations

    Meningioma, immunology

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

    numbers in document headers or citation references, particularly years or identification numbers.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     Wikimédia
    -0.81
    ESTRE
    -0.81
    talen
    -0.78
    に戻る
    -0.77
    getSimpleName
    -0.77
    /*
    -0.75
    gett
    -0.75
     Majesté
    -0.75
    ghz
    -0.74
    getCmp
    -0.73
    POSITIVE LOGITS
    plaatst
    0.90
     thru
    0.82
     mojo
    0.81
    abling
    0.80
     instances
    0.79
    terreno
    0.79
    tiness
    0.77
    lampada
    0.77
    ưở
    0.76
     gerekli
    0.76
    Activations Density 0.001%

    No Known Activations