© 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. 33837
    Prev
    Next
    INDEX
    Explanations

    phrases of description

    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
    tue
    -0.91
    thas
    -0.86
    THANK
    -0.86
    ceni
    -0.84
     отдельных
    -0.80
    ilitary
    -0.79
    eip
    -0.79
    craper
    -0.79
    ligence
    -0.79
     snippets
    -0.79
    POSITIVE LOGITS
     the
    1.33
     footage
    1.20
     vegetation
    1.14
     pixels
    1.13
     terreno
    1.07
     material
    1.05
     information
    1.03
     greenery
    1.02
     scenery
    1.02
     materiału
    1.02
    Activations Density 0.084%

    No Known Activations