© 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. 10-GEMMASCOPE-RES-131K
    7. 531
    Prev
    Next
    INDEX
    Explanations

    numbers and symbols

    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_10/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
     and
    -1.70
    ׇ
    -1.63
    fortunes
    -1.59
     imposs
    -1.56
     durables
    -1.53
    Zitat
    -1.49
     النبات
    -1.48
     aray
    -1.43
    Цены
    -1.41
     τῶν
    -1.40
    POSITIVE LOGITS
    ֶּ
    2.17
    ּוֹ
    1.97
    ַּ
    1.95
    ִּ
    1.91
    1.89
     more
    1.81
    ֵּ
    1.76
     
    1.61
    だよね
    1.53
    ָּ
    1.50
    Activations Density 0.001%
    No Known Activations