© 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. 117029
    Prev
    Next
    INDEX
    Explanations

    prepositions to introduce context

    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
    !!
    -0.07
    !!!!
    -0.06
    !.
    -0.06
     !!!
    -0.06
    ,-
    -0.06
    !!!!!
    -0.06
     ١
    -0.06
     Bernard
    -0.05
     oy
    -0.05
    POSITIVE LOGITS
     باید
    0.07
    通常
    0.07
     করতাম
    0.07
     обычно
    0.07
     înainte
    0.07
    Something
    0.07
     보통
    0.07
    を取
    0.07
    Within
    0.07
    Before
    0.07
    Activations Density 0.034%

    No Known Activations