© 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. 35949
    Prev
    Next
    INDEX
    Explanations

    string length calculations

    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
    因为
    -1.78
     menegaskan
    -1.72
    t
    -1.66
    焄
    -1.64
    泺
    -1.62
    s
    -1.60
     memperhatikan
    -1.57
     pagare
    -1.52
    ༑
    -1.50
    ኀ
    -1.50
    POSITIVE LOGITS
     of
    2.22
    很赞
    1.95
     includ
    1.91
     that
    1.88
    嵓
    1.75
    秾
    1.73
     its
    1.63
    that
    1.56
    銠
    1.56
     intermin
    1.55
    Activations Density 0.001%

    No Known Activations