© 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. 75054
    Prev
    Next
    INDEX
    Explanations

    superlatives and extremity

    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
     permite
    -1.62
     nimmer
    -1.45
     zatím
    -1.44
    蠓
    -1.43
     wenden
    -1.38
     ofrece
    -1.36
    ぐり
    -1.36
    ぐるみ
    -1.33
     partici
    -1.33
     capitaine
    -1.30
    POSITIVE LOGITS
    begin
    1.91
    you
    1.77
    because
    1.69
    see
    1.59
    also
    1.49
    just
    1.44
    only
    1.41
    when
    1.41
    number
    1.38
    what
    1.36
    Activations Density 0.014%

    No Known Activations