© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 16309
    Prev
    Next
    INDEX
    Explanations

    puppy or kitten

    np_acts-logits-general · gemini-2.5-flash-lite

    puppies and kittens

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    暌
    0.42
     marido
    0.41
     آهي
    0.40
     salaried
    0.40
    🗣
    0.39
     songwriting
    0.39
    aktadır
    0.39
     স্বামীর
    0.38
     husbands
    0.38
     marital
    0.38
    POSITIVE LOGITS
     puppy
    0.89
     puppies
    0.80
     Puppy
    0.77
     kitten
    0.73
     Newborn
    0.63
     kittens
    0.61
     seedling
    0.60
     Kitten
    0.58
    幼
    0.57
     seedlings
    0.57
    Activations Density 0.075%

    No Known Activations