© 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. 10-GEMMASCOPE-RES-131K
    7. 127289
    Prev
    Next
    INDEX
    Explanations

    hard + descriptive noun

    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
    Negative Logits
     tungkol
    -1.20
     ibang
    -1.10
    ᧐
    -1.09
    вший
    -1.09
     statuses
    -1.08
     bago
    -1.08
    CASA
    -1.07
     tanong
    -1.07
     $(\%)$
    -1.07
    ливо
    -1.07
    POSITIVE LOGITS
     hard
    1.59
     to
    1.53
     cualquier
    1.44
    Hard
    1.42
     geprü
    1.38
     två
    1.37
     sadece
    1.35
     dikembangkan
    1.32
     gezicht
    1.32
     nantinya
    1.32
    Activations Density 0.107%

    No Known Activations