© 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. 22-GEMMASCOPE-RES-131K
    7. 79630
    Prev
    Next
    INDEX
    Explanations

    code punctuation and disposal

    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_22/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
     equipamento
    -1.03
    pys
    -1.02
     estadia
    -0.98
    резать
    -0.98
    蝨
    -0.96
     RECOMMENDATIONS
    -0.95
     antigo
    -0.94
     elevador
    -0.94
    umptions
    -0.94
    ENNIS
    -0.93
    POSITIVE LOGITS
     and
    1.41
    although
    1.02
    bedienung
    1.00
    四大
    0.97
    کتور
    0.93
    不易
    0.91
     leaves
    0.90
    iarkan
    0.87
    ляр
    0.86
     Although
    0.85
    Activations Density 0.000%

    No Known Activations