© 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. 117471
    Prev
    Next
    INDEX
    Explanations

    various language characters

    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
    nothing
    -0.06
    place
    -0.06
    Override
    -0.06
     negativo
    -0.06
     ¨
    -0.06
     sufficient
    -0.06
     обеспечения
    -0.06
     NOTHING
    -0.06
     asign
    -0.06
     setzen
    -0.05
    POSITIVE LOGITS
     が
    0.08
    を見た
    0.07
     jadi
    0.07
     で
    0.07
    两者
    0.06
     while
    0.06
     を
    0.06
     While
    0.06
    첫
    0.06
    yards
    0.06
    Activations Density 0.001%

    No Known Activations