© 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. 10-GEMMASCOPE-RES-131K
    7. 42353
    Prev
    Next
    INDEX
    Explanations

    if not for

    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_10/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
     when
    -1.89
     When
    -1.73
     if
    -1.68
     cannot
    -1.65
     want
    -1.56
     cuando
    -1.51
     begin
    -1.47
     understand
    -1.45
     find
    -1.45
     different
    -1.41
    POSITIVE LOGITS
     ogranic
    1.42
     และ
    1.40
    ('--
    1.38
    ῤ
    1.38
     contextes
    1.35
     véhicules
    1.34
    撂
    1.32
    毟
    1.30
     nasze
    1.30
    xiii
    1.29
    Activations Density 0.008%

    No Known Activations