© 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. 75498
    Prev
    Next
    INDEX
    Explanations

    adjective following word or punctuation

    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
     some
    -1.57
     to
    -1.49
     mieście
    -1.46
     an
    -1.41
     several
    -1.36
     more
    -1.28
     our
    -1.24
     one
    -1.18
     many
    -1.16
     two
    -1.16
    POSITIVE LOGITS
     вас
    1.27
     вами
    1.25
    amaño
    1.25
     july
    1.25
     vedea
    1.24
    艸
    1.21
    這
    1.20
    部分を
    1.19
    不高
    1.17
     enfermos
    1.16
    Activations Density 0.101%

    No Known Activations