© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 94199
    Prev
    Next
    INDEX
    Explanations

    qualifying statements with "kind of"

    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
    Negative Logits
     dólares
    -0.90
     deliciosa
    -0.88
     Diar
    -0.88
     update
    -0.86
     voeten
    -0.83
    ){$
    -0.83
     acoged
    -0.82
    を設置
    -0.81
     équipe
    -0.77
    ёх
    -0.77
    POSITIVE LOGITS
     of
    3.66
    kinda
    1.22
    of
    1.15
     kinda
    1.13
    ของ
    1.08
     kind
    1.06
    kind
    0.91
     sort
    0.91
     của
    0.90
    sort
    0.89
    Activations Density 0.009%

    No Known Activations