© 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. 34-GEMMASCOPE-RES-131K
    7. 7332
    Prev
    Next
    INDEX
    Explanations

    adjectives tagged with _JJ

    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_34/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
     rudimentary
    -1.43
     meticulous
    -1.41
     noticeably
    -1.38
     weirdly
    -1.38
     meticulously
    -1.36
     touted
    -1.35
    そうですが
    -1.35
     wildly
    -1.34
     terribly
    -1.34
     horribly
    -1.33
    POSITIVE LOGITS
    /
    1.80
    preneurs
    1.47
     และ
    1.45
    -
    1.42
    datable
    1.41
    mability
    1.40
     durante
    1.37
    anced
    1.35
    panes
    1.34
    preneur
    1.33
    Activations Density 0.618%

    No Known Activations