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. 8918
    Prev
    Next
    INDEX
    Explanations

    On the

    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
     IMHO
    -0.79
    Sito
    -0.77
    contiguous
    -0.77
     igreja
    -0.77
    虞
    -0.75
    สะ
    -0.75
     Those
    -0.74
    ค่า
    -0.74
    渭
    -0.73
     lắng
    -0.72
    POSITIVE LOGITS
    unnamed
    0.91
     ‏
    0.89
     bụ
    0.88
    lude
    0.87
    imagining
    0.85
    definitely
    0.83
    simov
    0.83
    ølge
    0.82
    läufig
    0.82
    ÃO
    0.81
    Activations Density 0.000%

    No Known Activations