© 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. 117616
    Prev
    Next
    INDEX
    Explanations

    **color descriptions**

    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
     шаблон
    -0.06
     لأنه
    -0.06
     ఒక
    -0.06
     因為
    -0.06
    竟然
    -0.06
     altında
    -0.06
     ৮ম
    -0.06
     icin
    -0.06
     belongs
    -0.06
     경우에는
    -0.05
    POSITIVE LOGITS
     you
    0.07
     outcry
    0.07
    their
    0.06
     overly
    0.06
     their
    0.06
    onglet
    0.06
    ക്കുന്നത്
    0.06
     trickle
    0.06
    INSTR
    0.06
     discernible
    0.06
    Activations Density 0.001%

    No Known Activations