© 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. 4062
    Prev
    Next
    INDEX
    Explanations

    foundation for something

    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
    的角色
    -1.05
     młod
    -1.00
    emptyList
    -0.99
     samego
    -0.99
     ascertained
    -0.99
     yalnızca
    -0.96
     meisjes
    -0.94
    ᝰ
    -0.94
     deadline
    -0.92
    mariage
    -0.91
    POSITIVE LOGITS
     any
    1.93
     everything
    1.84
     all
    1.70
     much
    1.57
    所有的
    1.46
     most
    1.44
     successful
    1.43
     every
    1.43
     our
    1.42
     understanding
    1.40
    Activations Density 0.054%

    No Known Activations