© 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. 119496
    Prev
    Next
    INDEX
    Explanations

    in compliance

    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
     plusieurs
    -0.08
     several
    -0.08
     когда
    -0.08
     нескольких
    -0.07
     несколько
    -0.07
     няколко
    -0.07
     когато
    -0.07
     almost
    -0.07
     mehrere
    -0.07
     چندین
    -0.07
    POSITIVE LOGITS
     captures
    0.06
    Treas
    0.06
     indiv
    0.06
     rescat
    0.06
     captured
    0.06
     रोज़
    0.06
     ieri
    0.06
    Fisher
    0.06
     धूप
    0.06
    byter
    0.05
    Activations Density 0.004%

    No Known Activations