© 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. 22-GEMMASCOPE-RES-131K
    7. 71572
    Prev
    Next
    INDEX
    Explanations

    qualifying adverbs

    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
    pantalones
    -1.85
    
    -1.77
     and
    -1.71
     obviamente
    -1.70
     sandalias
    -1.70
     стоковые
    -1.68
     parachoque
    -1.63
    熜
    -1.62
    姎
    -1.60
    chaussures
    -1.59
    POSITIVE LOGITS
     to
    2.23
     the
    2.11
    the
    2.08
    ,
    2.03
     from
    2.02
     with
    1.95
     also
    1.84
     their
    1.82
     because
    1.82
     those
    1.80
    Activations Density 0.065%

    No Known Activations