Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 110027
    Prev
    Next
    INDEX
    Explanations

    names ending in 'li' or 'al'

    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
    atars
    -0.73
    鯊
    -0.71
     bột
    -0.70
     इत
    -0.70
    ilen
    -0.69
    пія
    -0.69
     Darn
    -0.69
     مستوى
    -0.69
    ikor
    -0.69
    rial
    -0.68
    POSITIVE LOGITS
    lng
    1.21
    liste
    0.97
    lli
    0.94
    seye
    0.83
    lk
    0.82
    lest
    0.81
    lust
    0.80
    ActionBar
    0.80
    lal
    0.78
    смотря
    0.78
    Activations Density 0.063%

    No Known Activations