© 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-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 21796
    Prev
    Next
    INDEX
    Explanations

    dog breeds and their physical traits

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     pet
    0.47
     cat
    0.44
     Pet
    0.44
     gatos
    0.42
     kitty
    0.42
    cat
    0.41
     Pets
    0.40
     novella
    0.40
    寵
    0.40
     pets
    0.40
    POSITIVE LOGITS
     endurance
    0.45
     Endurance
    0.45
    னீ
    0.42
    协同
    0.42
    etrain
    0.42
     sweat
    0.41
     sporty
    0.41
     stamina
    0.41
     breed
    0.41
     Finnish
    0.41
    Activations Density 0.047%

    No Known Activations