© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 11438
    Prev
    Next
    INDEX
    Explanations

    common prefixes of names

    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
    leggings
    -1.09
     nhat
    -1.05
     gustar
    -1.02
    が違う
    -0.98
     Võ
    -0.97
     empaque
    -0.96
     comprobar
    -0.96
    uteur
    -0.96
     garantia
    -0.95
     różnych
    -0.95
    POSITIVE LOGITS
     those
    1.02
     new
    0.95
     epitom
    0.92
     on
    0.91
    ？！
    0.89
     IN
    0.86
     extraordinarily
    0.84
     low
    0.84
     Those
    0.83
    ？（
    0.83
    Activations Density 0.001%

    No Known Activations