© 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. 120489
    Prev
    Next
    INDEX
    Explanations

    spatial dimensions and positioning

    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
     masculine
    -0.07
     protože
    -0.06
    女性
    -0.06
    长度
    -0.06
     river
    -0.06
     Timeline
    -0.06
     preachers
    -0.06
     हिन्दू
    -0.06
     Maroc
    -0.06
     traducción
    -0.06
    POSITIVE LOGITS
    Depois
    0.08
     вокруг
    0.07
    Après
    0.07
     Depois
    0.06
     all
    0.06
     anesthet
    0.06
     पागल
    0.06
    团
    0.06
     nearby
    0.06
    周囲
    0.06
    Activations Density 0.068%

    No Known Activations