© 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. 83295
    Prev
    Next
    INDEX
    Explanations

    durations of time ago

    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
    
    -1.00
     chì
    -1.00
    ोजना
    -0.99
    Ľ
    -0.98
     чёр
    -0.98
    mands
    -0.97
     byli
    -0.96
     popr
    -0.94
    erunner
    -0.93
    obut
    -0.92
    POSITIVE LOGITS
     of
    1.80
     into
    1.66
     have
    1.55
     has
    1.31
     spent
    1.21
     were
    1.19
     after
    1.16
     would
    1.14
     ago
    1.11
     went
    1.07
    Activations Density 0.015%

    No Known Activations