© 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. 34-GEMMASCOPE-RES-131K
    7. 73505
    Prev
    Next
    INDEX
    Explanations

    qualities of nouns

    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
     enormes
    -1.77
    鹋
    -1.66
     soooo
    -1.66
    
    -1.63
    荭
    -1.62
     sooo
    -1.61
    焌
    -1.61
    𓁹
    -1.59
    amazing
    -1.55
    inerario
    -1.55
    POSITIVE LOGITS
     but
    2.30
     and
    1.71
     increase
    1.55
     amount
    1.49
     set
    1.47
     after
    1.42
     although
    1.35
     Those
    1.33
     Schloß
    1.30
     February
    1.28
    Activations Density 0.751%

    No Known Activations