© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 58053
    Prev
    Next
    INDEX
    Explanations

    people associated with pets

    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
    Not in Any Lists

    No Comments

    Negative Logits
     Wasch
    -0.84
     owners
    -0.83
     Draht
    -0.80
    raster
    -0.77
     immunization
    -0.76
     young
    -0.73
     dewasa
    -0.71
    celtic
    -0.71
     monotony
    -0.70
     owner
    -0.69
    POSITIVE LOGITS
    Pet
    0.99
     Pet
    0.91
    ienne
    0.90
     ペット
    0.89
    pet
    0.89
    beruf
    0.86
    Animal
    0.86
    spinner
    0.82
     Animal
    0.81
    ัตว์
    0.79
    Activations Density 0.026%

    No Known Activations