© 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. 86801
    Prev
    Next
    INDEX
    Explanations

    warranty coverage and duration

    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
    
    -1.18
    ℟
    -1.16
     Совета
    -1.08
     relativement
    -1.05
     hallaz
    -1.05
    mitglieder
    -1.03
     Erfolge
    -1.02
    urora
    -1.02
    kabau
    -1.02
    ቨ
    -1.01
    POSITIVE LOGITS
     coverage
    1.46
     period
    1.41
     covering
    1.28
     covers
    1.21
     Periods
    1.13
     periods
    1.10
     покри
    1.09
     offered
    1.05
     durations
    1.05
     void
    1.03
    Activations Density 0.021%

    No Known Activations