© 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. 119706
    Prev
    Next
    INDEX
    Explanations

    names and titles

    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
    ,
    -0.07
     dummy
    -0.06
     quanto
    -0.06
    による
    -0.06
     dipende
    -0.06
     centers
    -0.06
     نحن
    -0.06
     $
    -0.06
    -
    -0.06
    根本
    -0.06
    POSITIVE LOGITS
    Some
    0.08
    SOME
    0.07
    注明
    0.06
     음식
    0.06
    রার
    0.06
    some
    0.06
     provide
    0.06
    versions
    0.06
     Some
    0.06
    Algun
    0.06
    Activations Density 0.008%

    No Known Activations