© 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. 69818
    Prev
    Next
    INDEX
    Explanations

    lecture notes and halls

    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
    釹
    -0.94
     个人
    -0.93
    d
    -0.93
     праздника
    -0.87
    O
    -0.84
     無地
    -0.82
    ?
    -0.82
    v
    -0.81
     partita
    -0.81
     maiores
    -0.81
    POSITIVE LOGITS
     series
    1.38
     SERIES
    1.20
    series
    1.18
     Delivered
    1.16
     hall
    1.16
     Lect
    1.11
    delivered
    1.11
     delivered
    1.10
     halls
    1.09
     Series
    1.07
    Activations Density 0.006%

    No Known Activations