© 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. 129367
    Prev
    Next
    INDEX
    Explanations

    remote places or distances

    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
    整個
    -0.06
     mythological
    -0.06
     coord
    -0.06
    সঙ্গ
    -0.06
    整个
    -0.06
    ໂຕ
    -0.06
     clerg
    -0.06
     including
    -0.05
     सम्पूर्ण
    -0.05
     секрета
    -0.05
    POSITIVE LOGITS
     Guam
    0.06
     gages
    0.06
     LEDs
    0.06
    Pred
    0.06
    LCD
    0.06
     diesem
    0.06
    instagram
    0.06
     quelques
    0.06
     qualifies
    0.06
    どちら
    0.05
    Activations Density 0.015%

    No Known Activations