© 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. 119502
    Prev
    Next
    INDEX
    Explanations

    street names and locations

    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
    🛰
    -0.06
     utilizamos
    -0.06
     summers
    -0.06
     राष्ट
    -0.06
    oterapia
    -0.06
    ジナル
    -0.06
     hoped
    -0.06
    (_)
    -0.06
    |_{
    -0.06
    하던
    -0.06
    POSITIVE LOGITS
     Ancient
    0.06
    Ancient
    0.06
     Hispanic
    0.06
     امکان
    0.06
     कानूनी
    0.06
     ancient
    0.06
    ȩ
    0.05
     திருக்கோ
    0.05
     ఘ
    0.05
    PUBLIC
    0.05
    Activations Density 0.088%

    No Known Activations