© 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. 55828
    Prev
    Next
    INDEX
    Explanations

    questions, troubleshooting, or errors

    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
     saumon
    -1.18
     nowadays
    -1.16
     meistens
    -1.11
     principalmente
    -1.10
     niektó
    -1.04
    rovna
    -1.02
     terutama
    -1.02
    如果有
    -1.01
    velocityY
    -1.00
     некоторы
    -0.98
    POSITIVE LOGITS
     when
    1.83
     When
    1.39
     tried
    1.34
     but
    1.30
     Perhaps
    1.25
     I
    1.23
     can
    1.21
     seems
    1.16
     could
    1.16
     když
    1.14
    Activations Density 0.488%

    No Known Activations