© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 2282
    Prev
    Next
    INDEX
    Explanations

    online discussions and comments

    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
    ிறது
    -0.88
    推特
    -0.81
    Oacute
    -0.81
    ꯀ
    -0.79
     ը
    -0.77
    деи
    -0.75
     DevComponents
    -0.74
    deps
    -0.74
    offsetX
    -0.71
     gibi
    -0.71
    POSITIVE LOGITS
     discussion
    1.08
     discussions
    1.00
     online
    0.98
     Internet
    0.97
     Keyboard
    0.96
     posting
    0.96
     topic
    0.93
    刷
    0.93
     comments
    0.92
     topics
    0.90
    Activations Density 0.009%

    No Known Activations