© 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. 90443
    Prev
    Next
    INDEX
    Explanations

    questions asking for results

    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
     quando
    -0.98
     poderosos
    -0.98
    קות
    -0.93
     czasem
    -0.92
     פשוט
    -0.91
     první
    -0.91
     možno
    -0.91
    ኤ
    -0.90
     Diſ
    -0.90
     energético
    -0.89
    POSITIVE LOGITS
     what
    2.16
     What
    1.72
     how
    1.62
     How
    1.46
     does
    1.44
     Is
    1.41
     Are
    1.39
     would
    1.30
    What
    1.29
     now
    1.28
    Activations Density 0.059%

    No Known Activations