© 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. 90799
    Prev
    Next
    INDEX
    Explanations

    take it easy

    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
    Faj
    -0.76
    曬
    -0.75
    illing
    -0.71
    ITZ
    -0.70
    pric
    -0.70
    addFlags
    -0.69
     soloist
    -0.69
    (−
    -0.69
     лен
    -0.68
     /.
    -0.68
    POSITIVE LOGITS
     easy
    3.11
     slow
    2.63
    easy
    2.36
     Easy
    2.19
    Easy
    2.17
    slow
    2.08
    Slow
    2.02
     Slow
    1.97
    EASY
    1.93
     EASY
    1.78
    Activations Density 0.025%

    No Known Activations