© 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. 22-GEMMASCOPE-RES-131K
    7. 70349
    Prev
    Next
    INDEX
    Explanations

    numbers and specific following tokens

    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_22/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
     When
    -1.74
     Since
    -1.70
     as
    -1.66
     However
    -1.62
     during
    -1.60
     by
    -1.58
     amid
    -1.57
     ketika
    -1.56
     perpetually
    -1.55
     garner
    -1.52
    POSITIVE LOGITS
     zoude
    1.98
    漚
    1.95
    祧
    1.95
     frança
    1.93
    >
    1.89
    に使用
    1.85
    //{
    1.85
    に使
    1.84
    を行い
    1.82
     lavable
    1.77
    Activations Density 0.041%

    No Known Activations