© 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. 3649
    Prev
    Next
    INDEX
    Explanations

    casting and molding

    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
    arashtra
    -0.88
     embroidered
    -0.80
    ٛ
    -0.79
     akumulator
    -0.77
     adsorbed
    -0.75
     Pussy
    -0.74
     Crunchy
    -0.71
    hagic
    -0.71
     nervosa
    -0.70
     lacquered
    -0.70
    POSITIVE LOGITS
     casting
    3.08
     cast
    2.84
     mold
    2.77
     casts
    2.75
     molds
    2.67
    casting
    2.45
     Casting
    2.36
    cast
    2.34
     mould
    2.33
    Casting
    2.33
    Activations Density 0.068%

    No Known Activations