© 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. 82956
    Prev
    Next
    INDEX
    Explanations

    winter and summer months

    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
     durante
    -1.13
     helados
    -0.94
     DURING
    -0.91
    氿
    -0.91
     wist
    -0.89
     recomendado
    -0.88
     desperdic
    -0.88
    Ngay
    -0.87
     betrug
    -0.87
     abuso
    -0.86
    POSITIVE LOGITS
     months
    2.55
    months
    1.68
     season
    1.47
     seasons
    1.38
     hours
    1.35
     Months
    1.32
    Months
    1.22
     when
    1.20
     weeks
    1.20
     days
    1.14
    Activations Density 0.018%

    No Known Activations