© 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. 117087
    Prev
    Next
    INDEX
    Explanations

    street battle

    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
     people
    -0.07
     곳
    -0.06
     UUID
    -0.06
     are
    -0.06
     panorama
    -0.06
     +-
    -0.06
     one
    -0.06
     apartment
    -0.05
    WIT
    -0.05
     landscape
    -0.05
    POSITIVE LOGITS
     considera
    0.07
     previamente
    0.06
    重要な
    0.06
    pgamma
    0.06
     considerar
    0.06
     pre
    0.06
     virulent
    0.06
     করেছিল
    0.06
    接近
    0.06
    though
    0.06
    Activations Density 0.007%

    No Known Activations