© 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. 98009
    Prev
    Next
    INDEX
    Explanations

    signs conveying messages

    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
    represented
    -1.02
    ियों
    -0.85
    defined
    -0.84
    vodu
    -0.84
    called
    -0.81
    utilizzo
    -0.81
     Figures
    -0.80
    david
    -0.79
    になると
    -0.79
     düşünü
    -0.79
    POSITIVE LOGITS
     stating
    1.79
     proclaiming
    1.79
     saying
    1.66
     declaring
    1.55
     announcing
    1.52
     says
    1.47
     listing
    1.46
     proclaim
    1.42
     featuring
    1.40
     promoting
    1.38
    Activations Density 0.079%

    No Known Activations