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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 7537
    Prev
    Next
    INDEX
    Explanations

    end of question

    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
     этого
    -0.99
    Punk
    -0.87
    lected
    -0.82
    たまに
    -0.80
    大好きな
    -0.80
     außerdem
    -0.79
     Dada
    -0.79
     daarbij
    -0.79
     gustaría
    -0.78
    \_
    -0.78
    POSITIVE LOGITS
    AddHtmlAttribute
    0.95
     brutal
    0.90
     arkas
    0.86
     slad
    0.84
    idung
    0.84
    漬
    0.82
     ə
    0.82
    قلاب
    0.80
     douceur
    0.80
    Tó
    0.79
    Activations Density 0.030%

    No Known Activations