© 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. 10-GEMMASCOPE-RES-131K
    7. 105319
    Prev
    Next
    INDEX
    Explanations

    years or specific dates

    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_10/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
    🦶
    -1.52
    還能
    -1.48
    導致
    -1.44
    јани
    -1.41
    鋅
    -1.41
     персонал
    -1.38
    Awal
    -1.36
     EFFECT
    -1.36
    همه
    -1.35
     موب
    -1.34
    POSITIVE LOGITS
     because
    2.19
     we
    1.95
     since
    1.90
     has
    1.72
    ?
    1.66
     that
    1.62
     a
    1.58
     from
    1.52
    >
    1.51
     part
    1.46
    Activations Density 0.182%

    No Known Activations