© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 130249
    Prev
    Next
    INDEX
    Explanations

    legal action and consequences

    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
     your
    -1.13
    Còn
    -1.09
     šed
    -1.03
     اپنے
    -1.02
     bílé
    -1.02
    Fluorescence
    -1.02
     jawaban
    -1.00
     vielleicht
    -0.99
     you
    -0.99
    namientos
    -0.96
    POSITIVE LOGITS
     because
    1.25
     was
    1.13
     when
    1.10
     GmbH
    1.03
     workers
    1.03
     OGSÅ
    1.02
    '>";
    1.01
     manager
    0.98
    unsafe
    0.98
    онка
    0.97
    Activations Density 0.002%

    No Known Activations