© 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-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 120285
    Prev
    Next
    INDEX
    Explanations

    spatial distance

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/gemma-4-saes/gemma-4-31b
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     kepercayaan
    -0.06
     pojed
    -0.06
     współ
    -0.06
    ひとつ
    -0.06
     upward
    -0.06
     inwards
    -0.06
     satunya
    -0.06
     چاہی
    -0.06
     uppermost
    -0.06
     অঞ্চল
    -0.06
    POSITIVE LOGITS
     distancing
    0.07
     distancia
    0.06
     six
    0.06
     five
    0.06
     afast
    0.06
     Maroc
    0.06
     Moroccan
    0.06
    𝑜
    0.06
    Restore
    0.06
     dices
    0.06
    Activations Density 0.014%

    No Known Activations