© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 110963
    Prev
    Next
    INDEX
    Explanations

    Apple app bundles and file paths

    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_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
     PML
    -0.77
    ポリ
    -0.71
     Mariners
    -0.70
    クー
    -0.69
     greco
    -0.69
    POL
    -0.68
     doigt
    -0.68
     Funcion
    -0.68
     bosco
    -0.66
    ᝰ
    -0.66
    POSITIVE LOGITS
     bundle
    1.41
     Bundle
    1.31
    Bundle
    1.20
     bundles
    1.16
    bundle
    1.16
     Documents
    1.16
    documents
    1.15
     documents
    1.13
    Documents
    1.01
    沙
    1.00
    Activations Density 0.122%

    No Known Activations