© 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. 54443
    Prev
    Next
    INDEX
    Explanations

    when applicable

    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
    ⢻
    -0.94
     apporter
    -0.93
     célè
    -0.88
    kaç
    -0.88
     préf
    -0.87
    द्धि
    -0.85
    licópter
    -0.84
    Berat
    -0.84
     bénéficier
    -0.84
    vén
    -0.83
    POSITIVE LOGITS
     default
    1.11
     when
    1.11
     appropriate
    1.04
     for
    1.00
     applicable
    0.98
     if
    0.98
     how
    0.94
     When
    0.93
     для
    0.91
     normal
    0.91
    Activations Density 0.059%

    No Known Activations