© 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. 86781
    Prev
    Next
    INDEX
    Explanations

    Qt framework code

    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
     signals
    -1.01
    signal
    -1.00
    signals
    -0.96
     signal
    -0.92
    Signal
    -0.85
     Signals
    -0.81
    SIGNAL
    -0.76
     signaled
    -0.75
    ([^
    -0.75
     golfer
    -0.74
    POSITIVE LOGITS
    стема
    0.82
     CONFIG
    0.76
    Enquiries
    0.75
    事务
    0.74
     فيها
    0.73
    hasNext
    0.71
    ooplankton
    0.71
     الخ
    0.70
    ject
    0.70
     kompakt
    0.69
    Activations Density 0.025%

    No Known Activations