© 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. 82523
    Prev
    Next
    INDEX
    Explanations

    call to schedule or inquire

    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
     jendela
    -0.93
     Danach
    -0.92
     パッケージ
    -0.91
     havia
    -0.90
     unmittel
    -0.88
     réforme
    -0.85
     sepatu
    -0.85
    ͧ
    -0.85
     they
    -0.82
     entsprechenden
    -0.82
    POSITIVE LOGITS
     schedule
    1.23
     online
    1.18
     Schedule
    1.13
    schedule
    1.09
    request
    1.09
    online
    1.04
    REQUEST
    1.02
    Schedule
    0.96
     fill
    0.96
    SCHEDULE
    0.93
    Activations Density 0.014%

    No Known Activations