© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 66170
    Prev
    Next
    INDEX
    Explanations

    tickets

    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
     this
    -0.97
     at
    -0.95
     in
    -0.93
     בתח
    -0.86
     one
    -0.84
     well
    -0.83
     oddly
    -0.82
     their
    -0.79
     on
    -0.78
    مرة
    -0.77
    POSITIVE LOGITS
     tickets
    1.00
    witches
    1.00
    
    0.99
    olja
    0.96
     paroisse
    0.93
    🤳
    0.93
     Tickets
    0.93
    𝓤
    0.91
    ୫
    0.91
    RESULTS
    0.91
    Activations Density 0.024%

    No Known Activations