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. 7778
    Prev
    Next
    INDEX
    Explanations

    key-related access

    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
     彩色
    -0.76
    หรับ
    -0.74
     Specialization
    -0.71
     columnIndex
    -0.68
     đình
    -0.68
     потом
    -0.68
    딧
    -0.68
    יצוב
    -0.68
    masque
    -0.68
    Checkpoint
    -0.67
    POSITIVE LOGITS
     keys
    4.09
     key
    4.09
    key
    3.23
    keys
    3.13
    Key
    3.11
     Keys
    3.05
    Keys
    2.98
    KEY
    2.98
     Key
    2.94
     клю
    2.83
    Activations Density 0.092%

    No Known Activations