© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 59559
    Prev
    Next
    INDEX
    Explanations

    timeless enduring classics

    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
     darbo
    -0.89
    PATIENT
    -0.85
    itized
    -0.82
     reciente
    -0.82
     москва
    -0.81
    klád
    -0.80
    álního
    -0.80
    itie
    -0.80
     nivå
    -0.79
     ブルゾン
    -0.79
    POSITIVE LOGITS
     timeless
    4.28
     Timeless
    2.89
     evergreen
    2.58
     eternal
    2.16
     classics
    2.16
     classic
    2.08
     enduring
    1.98
     perennial
    1.90
    classic
    1.89
     everlasting
    1.80
    Activations Density 0.037%

    No Known Activations